Search

The majority of theoretical analyses of evolutionary algorithms in the discrete domain focus on binary optimization algorithms, even though black-box optimization on the categorical domain has a lot of practical applications. In this paper, we consider a probabilistic model-based algorithm using the family of categorical distributions as its underlying distribution and set the sample size as two. We term this specific algorithm the categorical compact genetic algorithm (ccGA). The ccGA can be considered as an extension of the compact genetic algorithm (cGA), which is an efficient binary optimization algorithm. We theoretically analyze the dependency of the number of possible categories $K$, the number of dimensions $D$, and the learning rate $\eta$ on the runtime. We investigate the tail bound of the runtime on two typical linear functions on the categorical domain: categorical OneMax (COM) and KVal. We derive that the runtimes on COM and KVal are $O(\sqrt{D} \ln (DK) / \eta)$ and $\Theta(D \ln K/ \eta)$ with high probability, respectively. Our analysis is a generalization for that of the cGA on the binary domain.

Research on vessel automation and autonomy is currently being conducted by various countries and institutions. Safe and accurate ship control algorithms are crucial to realize automated operation. Actuator drive constraints of a target ship may jeopardize the stability of the control law and require complex theory. In this study, we include a penalty term to the control law gain optimization stage of dynamic positioning systems to account for the amounts by which the actuator input value and its rate of change exceed the constraint. The parameters for generating a suitable reference path for the control law are identified simultaneously with the control gains. The simulation results show that the proposed method can realize control parameters and a reference design with excellent tracking performance while determining the cost of the controller design by considering the effects of both the actuators and rate saturation., Comment: 9 pages, 5 figures, preprint submitted to the Journal of Marine Science and Technology

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the language model policy to maximize reward under a safety constraint, and then proposes an algorithm, Stepwise Alignment for Constrained Policy Optimization (SACPO). One key idea behind SACPO, supported by theory, is that the optimal policy incorporating reward and safety can be directly obtained from a reward-aligned policy. Building on this key idea, SACPO aligns LLMs step-wise with each metric while leveraging simple yet powerful alignment algorithms such as direct preference optimization (DPO). SACPO offers several advantages, including simplicity, stability, computational efficiency, and flexibility of algorithms and datasets. Under mild assumptions, our theoretical analysis provides the upper bounds on optimality and safety constraint violation. Our experimental results show that SACPO can fine-tune Alpaca-7B better than the state-of-the-art method in terms of both helpfulness and harmlessness.

The covariance matrix adaptation evolution strategy (CMA-ES) is one of the most successful methods for solving continuous black-box optimization problems. A practically useful aspect of the CMA-ES is that it can be used without hyperparameter tuning. However, the hyperparameter settings still have a considerable impact on performance, especially for difficult tasks, such as solving multimodal or noisy problems. This study comprehensively explores the impact of learning rate on the CMA-ES performance and demonstrates the necessity of a small learning rate by considering ordinary differential equations. Thereafter, it discusses the setting of an ideal learning rate. Based on these discussions, we develop a novel learning rate adaptation mechanism for the CMA-ES that maintains a constant signal-to-noise ratio. Additionally, we investigate the behavior of the CMA-ES with the proposed learning rate adaptation mechanism through numerical experiments, and compare the results with those obtained for the CMA-ES with a fixed learning rate and with population size adaptation. The results show that the CMA-ES with the proposed learning rate adaptation works well for multimodal and/or noisy problems without extremely expensive learning rate tuning., Comment: Under review for ACM TELO

In black-box optimization, noise in the objective function is inevitable. Noise disrupts the ranking of candidate solutions in comparison-based optimization, possibly deteriorating the search performance compared with a noiseless scenario. Explicit averaging takes the sample average of noisy objective function values and is widely used as a simple and versatile noise-handling technique. Although it is suitable for various applications, it is ineffective if the mean is not finite. We theoretically reveal that explicit averaging has a negative effect on the estimation of ground-truth rankings when assuming stably distributed noise without a finite mean. Alternatively, sign averaging is proposed as a simple but robust noise-handling technique. We theoretically prove that the sign averaging estimates the order of the medians of the noisy objective function values of a pair of points with arbitrarily high probability as the number of samples increases. Its advantages over explicit averaging and its robustness are also confirmed through numerical experiments., Comment: 13 pages, 1 figures

In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LLMs is alignment with humans achieved with Reinforcement Learning from Human Feedback (RLHF), as for many LLMs such as GPT-4, Bard, etc. In addition, recent studies are investigating the replacement of human feedback with feedback from other LLMs named Reinforcement Learning from AI Feedback (RLAIF). We examine the biases that come along with evaluating LLMs with other LLMs and take a closer look into verbosity bias -- a bias where LLMs sometimes prefer more verbose answers even if they have similar qualities. We see that in our problem setting, GPT-4 prefers longer answers more than humans. We also propose a metric to measure this bias.

A dynamic model for an automatic berthing and unberthing controller has to estimate harbor maneuvers, which include berthing, unberthing, approach maneuvers to berths, and entering and leaving the port. When the dynamic model is estimated by the system identification, a large number of tests or trials are required to measure the various motions of harbor maneuvers. However, the amount of data that can be obtained is limited due to the high costs and time-consuming nature of full-scale ship trials. In this paper, we improve the generalization performance of the dynamic model for the automatic berthing and unberthing controller by introducing data augmentation. This study used slicing and jittering as data augmentation methods and confirmed their effectiveness by numerical experiments using the free-running model tests. The dynamic model is represented by a neural network-based model in numerical experiments. Results of numerical experiments demonstrated that slicing and jittering are effective data augmentation methods but could not improve generalization performance for extrapolation states of the original dataset., Comment: 12 pages, 11 figures, Submitted to Journal of Marine Science and Technology

A concept-based classifier can explain the decision process of a deep learning model by human-understandable concepts in image classification problems. However, sometimes concept-based explanations may cause false positives, which misregards unrelated concepts as important for the prediction task. Our goal is to find the statistically significant concept for classification to prevent misinterpretation. In this study, we propose a method using a deep learning model to learn the image concept and then using the Knockoff samples to select the important concepts for prediction by controlling the False Discovery Rate (FDR) under a certain value. We evaluate the proposed method in our synthetic and real data experiments. Also, it shows that our method can control the FDR properly while selecting highly interpretable concepts to improve the trustworthiness of the model., Comment: Accepted to IJCAI'23

The covariance matrix adaptation evolution strategy (CMA-ES) is one of the most successful methods for solving black-box continuous optimization problems. One practically useful aspect of the CMA-ES is that it can be used without hyperparameter tuning. However, the hyperparameter settings still have a considerable impact, especially for difficult tasks such as solving multimodal or noisy problems. In this study, we investigate whether the CMA-ES with default population size can solve multimodal and noisy problems. To perform this investigation, we develop a novel learning rate adaptation mechanism for the CMA-ES, such that the learning rate is adapted so as to maintain a constant signal-to-noise ratio. We investigate the behavior of the CMA-ES with the proposed learning rate adaptation mechanism through numerical experiments, and compare the results with those obtained for the CMA-ES with a fixed learning rate. The results demonstrate that, when the proposed learning rate adaptation is used, the CMA-ES with default population size works well on multimodal and/or noisy problems, without the need for extremely expensive learning rate tuning., Comment: Nominated for the best paper of GECCO'23 ENUM Track. We have corrected the error of Eq.(7)

In this study, we consider a continuous min--max optimization problem $\min_{x \in \mathbb{X} \max_{y \in \mathbb{Y}}}f(x,y)$ whose objective function is a black-box. We propose a novel approach to minimize the worst-case objective function $F(x) = \max_{y} f(x,y)$ directly using a covariance matrix adaptation evolution strategy (CMA-ES) in which the rankings of solution candidates are approximated by our proposed worst-case ranking approximation (WRA) mechanism. We develop two variants of WRA combined with CMA-ES and approximate gradient ascent as numerical solvers for the inner maximization problem. Numerical experiments show that our proposed approach outperforms several existing approaches when the objective function is a smooth strongly convex--concave function and the interaction between $x$ and $y$ is strong. We investigate the advantages of the proposed approach for problems where the objective function is not limited to smooth strongly convex--concave functions. The effectiveness of the proposed approach is demonstrated in the robust berthing control problem with uncertainty.ngly convex--concave functions. The effectiveness of the proposed approach is demonstrated in the robust berthing control problem with uncertainty.

A simulation environment of harbor maneuvers is critical for developing automatic berthing. Dynamic models are widely used to estimate harbor maneuvers. However, human decision-making and data analysis are necessary to derive, select, and identify the model because each actuator configuration needs an inherent mathematical expression. We proposed a new dynamic model for arbitrary configurations to overcome that issue. The new model is a hybrid model that combines the simplicity of the derivation of the Taylor expansion and the high degree of freedom of the MMG low-speed maneuvering model. We also developed a method to select mathematical expressions for the proposed model using system identification. Because the proposed model can easily derive mathematical expressions, we can generate multiple models simultaneously and choose the best one. This method can reduce the workload of model identification and selection. Furthermore, the proposed method will enable the automatic generation of dynamic models because it can reduce human decision-making and data analysis for the model generation due to its less dependency on the knowledge of ship hydrodynamics and captive model test. The proposed method was validated with free-running model tests and showed equivalent or better estimation performance than the conventional model generation method., Comment: 30 pages, 11 figures, a preprint under review

We investigate policy transfer using image-to-semantics translation to mitigate learning difficulties in vision-based robotics control agents. This problem assumes two environments: a simulator environment with semantics, that is, low-dimensional and essential information, as the state space, and a real-world environment with images as the state space. By learning mapping from images to semantics, we can transfer a policy, pre-trained in the simulator, to the real world, thereby eliminating real-world on-policy agent interactions to learn, which are costly and risky. In addition, using image-to-semantics mapping is advantageous in terms of the computational efficiency to train the policy and the interpretability of the obtained policy over other types of sim-to-real transfer strategies. To tackle the main difficulty in learning image-to-semantics mapping, namely the human annotation cost for producing a training dataset, we propose two techniques: pair augmentation with the transition function in the simulator environment and active learning. We observed a reduction in the annotation cost without a decline in the performance of the transfer, and the proposed approach outperformed the existing approach without annotation., Comment: The 2022 International Joint Conference on Neural Networks (IJCNN2022)

Automation of berthing maneuvers in shipping is a pressing issue as the berthing maneuver is one of the most stressful tasks seafarers undertake. Berthing control problems are often tackled via tracking a predefined trajectory or path. Maintaining a tracking error of zero under an uncertain environment is impossible; the tracking controller is nonetheless required to bring vessels close to desired berths. The tracking controller must prioritize the avoidance of tracking errors that may cause collisions with obstacles. This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles. Via numerical simulations, we show that the proposed method reduces the probability of collisions during berthing maneuvers. Furthermore, this paper shows the tracking performance in a model experiment., Comment: 14 pages, 15 figures, Submitted to Journal of Marine Science and Technology

In this study, we consider simulation-based worst-case optimization problems with continuous design variables and a finite scenario set. To reduce the number of simulations required and increase the number of restarts for better local optimum solutions, we propose a new approach referred to as adaptive scenario subset selection (AS3). The proposed approach subsamples a scenario subset as a support to construct the worst-case function in a given neighborhood, and we introduce such a scenario subset. Moreover, we develop a new optimization algorithm by combining AS3 and the covariance matrix adaptation evolution strategy (CMA-ES), denoted AS3-CMA-ES. At each algorithmic iteration, a subset of support scenarios is selected, and CMA-ES attempts to optimize the worst-case objective computed only through a subset of the scenarios. The proposed algorithm reduces the number of simulations required by executing simulations on only a scenario subset, rather than on all scenarios. In numerical experiments, we verified that AS3-CMA-ES is more efficient in terms of the number of simulations than the brute-force approach and a surrogate-assisted approach lq-CMA-ES when the ratio of the number of support scenarios to the total number of scenarios is relatively small. In addition, the usefulness of AS3-CMA-ES was evaluated for well placement optimization for carbon dioxide capture and storage (CCS). In comparison with the brute-force approach and lq-CMA-ES, AS3-CMA-ES was able to find better solutions because of more frequent restarts.

In the field of reinforcement learning, because of the high cost and risk of policy training in the real world, policies are trained in a simulation environment and transferred to the corresponding real-world environment. However, the simulation environment does not perfectly mimic the real-world environment, lead to model misspecification. Multiple studies report significant deterioration of policy performance in a real-world environment. In this study, we focus on scenarios involving a simulation environment with uncertainty parameters and the set of their possible values, called the uncertainty parameter set. The aim is to optimize the worst-case performance on the uncertainty parameter set to guarantee the performance in the corresponding real-world environment. To obtain a policy for the optimization, we propose an off-policy actor-critic approach called the Max-Min Twin Delayed Deep Deterministic Policy Gradient algorithm (M2TD3), which solves a max-min optimization problem using a simultaneous gradient ascent descent approach. Experiments in multi-joint dynamics with contact (MuJoCo) environments show that the proposed method exhibited a worst-case performance superior to several baseline approaches., Comment: Neural Information Processing Systems 2022 (NeurIPS '22)

Evolution strategy (ES) is one of promising classes of algorithms for black-box continuous optimization. Despite its broad successes in applications, theoretical analysis on the speed of its convergence is limited on convex quadratic functions and their monotonic transformation. In this study, an upper bound and a lower bound of the rate of linear convergence of the (1+1)-ES on locally $L$-strongly convex functions with $U$-Lipschitz continuous gradient are derived as $\exp\left(-\Omega_{d\to\infty}\left(\frac{L}{d\cdot U}\right)\right)$ and $\exp\left(-\frac1d\right)$, respectively. Notably, any prior knowledge on the mathematical properties of the objective function such as Lipschitz constant is not given to the algorithm, whereas the existing analyses of derivative-free optimization algorithms require them., Comment: 15 pages

In real-world applications of multi-class classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., speed limit). In this paper, we propose a loss function that can improve the recall of an important class while maintaining the same level of accuracy as the case using cross-entropy loss. For our purpose, we need to make the separation of the important class better than the other classes. However, existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. On the other hand, the method that gives a margin to the angle between the feature vectors and the weight vectors of the last fully connected layer corresponding to each feature can improve the separation. Therefore, we propose a loss function that can improve the separation of the important class by setting the margin only for the important class, called Class-sensitive Additive Angular Margin Loss (CAMRI Loss). CAMRI loss is expected to reduce the variance of angles between features and weights of the important class relative to other classes due to the margin around the important class in the feature space by adding a penalty to the angle. In addition, concentrating the penalty only on the important classes hardly sacrifices the separation of the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that the proposed method could improve up to 9% recall improvement on cross-entropy loss without sacrificing accuracy., Comment: 2022 International Joint Conference on Neural Networks (IJCNN 2022)

In this study, we investigate the problem of min-max continuous optimization in a black-box setting $\min_{x} \max_{y}f(x,y)$. A popular approach updates $x$ and $y$ simultaneously or alternatingly. However, two major limitations have been reported in existing approaches. (I) As the influence of the interaction term between $x$ and $y$ (e.g., $x^\mathrm{T} B y$) on the Lipschitz smooth and strongly convex-concave function $f$ increases, the approaches converge to an optimal solution at a slower rate. (II) The approaches fail to converge if $f$ is not Lipschitz smooth and strongly convex-concave around the optimal solution. To address these difficulties, we propose minimizing the worst-case objective function $F(x)=\max_{y}f(x,y)$ directly using the covariance matrix adaptation evolution strategy, in which the rankings of solution candidates are approximated by our proposed worst-case ranking approximation (WRA) mechanism. Compared with existing approaches, numerical experiments show two important findings regarding our proposed method. (1) The proposed approach is efficient in terms of $f$-calls on a Lipschitz smooth and strongly convex-concave function with a large interaction term. (2) The proposed approach can converge on functions that are not Lipschitz smooth and strongly convex-concave around the optimal solution, whereas existing approaches fail., Comment: accepted for GECCO 2022

A surrogate function is often employed to reduce the number of objective function evaluations for optimization. However, the effect of using a surrogate model in evolutionary approaches has not been theoretically investigated. This paper theoretically analyzes the information-geometric optimization framework using a surrogate function. The value of the expected objective function under the candidate sampling distribution is used as the measure of progress of the algorithm. We assume that the surrogate function is maintained so that the population version of the Kendall's rank correlation coefficient between the surrogate function and the objective function under the candidate sampling distribution is greater than or equal to a predefined threshold. We prove that information-geometric optimization using such a surrogate function leads to a monotonic decrease in the expected objective function value if the threshold is sufficiently close to one. The acceptable threshold value is analyzed for the case of the information-geometric optimization instantiated with Gaussian distributions, i.e., the rank-$\mu$ update CMA-ES, on a convex quadratic objective function. As an alternative to the Kendall's rank correlation coefficient, we investigate the use of the Pearson correlation coefficient between the weights assigned to candidate solutions based on the objective function and the surrogate function., Comment: accepted for GECCO 2022

This paper proposes a two-phase framework with a B\'{e}zier simplex-based interpolation method (TPB) for computationally expensive multi-objective optimization. The first phase in TPB aims to approximate a few Pareto optimal solutions by optimizing a sequence of single-objective scalar problems. The first phase in TPB can fully exploit a state-of-the-art single-objective derivative-free optimizer. The second phase in TPB utilizes a B\'{e}zier simplex model to interpolate the solutions obtained in the first phase. The second phase in TPB fully exploits the fact that a B\'{e}zier simplex model can approximate the Pareto optimal solution set by exploiting its simplex structure when a given problem is simplicial. We investigate the performance of TPB on the 55 bi-objective BBOB problems. The results show that TPB performs significantly better than HMO-CMA-ES and some state-of-the-art meta-model-based optimizers., Comment: This is an accepted version of a paper published in the proceedings of GECCO 2022

Accurate maneuvering estimation is essential to establish autonomous berthing control. The system-based mathematical model is widely used to estimate the ship's maneuver. Commonly, the system parameters of the mathematical model are obtained by the captive model test (CMT), which is time-consuming to construct an accurate model suitable for complex berthing maneuvers. System identification (SI) is an alternative to constructing the mathematical model. However, SI on the mathematical model of ship's maneuver has been only conducted on much simpler maneuver: turning and zig-zag. Therefore, this study investigates the SI on a mathematical model capable of berthing maneuver. The main contributions of this study are as follows: (i) construct the system-based mathematical model on berthing by optimizing system parameters with a reduced amount of model tests than the CMT-based scheme; (ii) Find the favorable choice of objective function and type of training data for optimization. Global optimization scheme CMA-ES explored the system parameters of the MMG model from the free-running model's trajectories. The berthing simulation with the parameters obtained by the proposed method showed better agreement with the free-running model test than parameters obtained by the CMT. Furthermore, the proposed method required fewer data amounts than a CMT-based scheme., Comment: 16 pages, 8 figures, preprint

Several studies on ship maneuvering models have been conducted using captive model tests or computational fluid dynamics (CFD) and physical models, such as the maneuvering modeling group (MMG) model. A new system identification method for generating a low-speed maneuvering model using recurrent neural networks (RNNs) and free running model tests is proposed in this study. We especially focus on a low-speed maneuver such as the final phase in berthing to achieve automatic berthing control. Accurate dynamic modeling with minimum modeling error is highly desired to establish a model-based control system. We propose a new loss function that reduces the effect of the noise included in the training data. Besides, we revealed the following facts - an RNN that ignores the memory before a certain time improved the prediction accuracy compared with the "standard" RNN, and the random maneuver test was effective in obtaining an accurate berthing maneuver model. In addition, several low-speed free running model tests were performed for the scale model of the M.V. Esso Osaka. As a result, this paper showed that the proposed method using a neural network model could accurately represent low-speed maneuvering motions., Comment: 13 pages, 7 figures, submitted to Journal of Marine Science and Technology for peer-review

We aim to explain a black-box classifier with the form: `data X is classified as class Y because X \textit{has} A, B and \textit{does not have} C' in which A, B, and C are high-level concepts. The challenge is that we have to discover in an unsupervised manner a set of concepts, i.e., A, B and C, that is useful for the explaining the classifier. We first introduce a structural generative model that is suitable to express and discover such concepts. We then propose a learning process that simultaneously learns the data distribution and encourages certain concepts to have a large causal influence on the classifier output. Our method also allows easy integration of user's prior knowledge to induce high interpretability of concepts. Using multiple datasets, we demonstrate that our method can discover useful binary concepts for explanation.

To realize autonomous shipping, autonomous berthing and unberthing are some of the technical challenges. In the past, numerous research have been done on the optimization of trajectory planning of berthing problems. However, these studies assumed only a simple berth and did not consider obstacles. Optimization of trajectory planning on berthing and unberthing in actual ports must consider the spatial constraints and maintain sufficient distance to obstacles. The main contributions of this study are as follows: (i) a collision avoidance algorithm based on the ship domain which has variable size by the ship speed is proposed, to include the spatial constraints to optimization; (ii) the effect of wind disturbance is taken into account to the trajectory planning to make a feasible trajectory based on the capacity limit of actuators; (iii) showing that the optimization method for berthing is also eligible for the unberthing, which has been almost neglected; (iv) waypoints are included to the optimization process, to make optimization easier on practical applications. The authors tested the proposed method on two existing ports. The proposed method performed well on both the berthing and the unberthing problem and optimized the control input and the trajectory while avoiding collision with the complex obstacles., Comment: 19 pages, 17 figures, Published on Ocean Engineering

We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately. We analyze its convergence property on a strongly convex--concave problem and show its linear convergence toward the global min--max saddle point. Based on the convergence analysis, we develop a heuristic approach to adapt the learning rate. An implementation of the developed approach using the (1+1)-CMA-ES as the minimization oracle, namely Adversarial-CMA-ES, is shown to outperform several existing approaches on test problems. Numerical evaluation confirms the tightness of the theoretical convergence rate bound as well as the efficiency of the learning rate adaptation mechanism. As an example of real-world problems, the suggested optimization method is applied to automatic berthing control problems under model uncertainties, showing its usefulness in obtaining solutions robust to uncertainty., Comment: Accepted for ACM TELO

Video game level generation based on machine learning (ML), in particular, deep generative models, has attracted attention as a technique to automate level generation. However, applications of existing ML-based level generations are mostly limited to tile-based level representation. When ML techniques are applied to game domains with non-tile-based level representation, such as Angry Birds, where objects in a level are specified by real-valued parameters, ML often fails to generate playable levels. In this study, we develop a deep-generative-model-based level generation for the game domain of Angry Birds. To overcome these drawbacks, we propose a sequential encoding of a level and process it as text data, whereas existing approaches employ a tile-based encoding and process it as an image. Experiments show that the proposed level generator drastically improves the stability and diversity of generated levels compared with existing approaches. We apply latent variable evolution with the proposed generator to control the feature of a generated level computed through an AI agent's play, while keeping the level stable and natural., Comment: The Genetic and Evolutionary Computation Conference 2021 (GECCO '21)

A major approach to saddle point optimization $\min_x\max_y f(x, y)$ is a gradient based approach as is popularized by generative adversarial networks (GANs). In contrast, we analyze an alternative approach relying only on an oracle that solves a minimization problem approximately. Our approach locates approximate solutions $x'$ and $y'$ to $\min_{x'}f(x', y)$ and $\max_{y'}f(x, y')$ at a given point $(x, y)$ and updates $(x, y)$ toward these approximate solutions $(x', y')$ with a learning rate $\eta$. On locally strong convex--concave smooth functions, we derive conditions on $\eta$ to exhibit linear convergence to a local saddle point, which reveals a possible shortcoming of recently developed robust adversarial reinforcement learning algorithms. We develop a heuristic approach to adapt $\eta$ derivative-free and implement zero-order and first-order minimization algorithms. Numerical experiments are conducted to show the tightness of the theoretical results as well as the usefulness of the $\eta$ adaptation mechanism., Comment: Accepted for GECCO 2021

The (1+1)-evolution strategy (ES) with success-based step-size adaptation is analyzed on a general convex quadratic function and its monotone transformation, that is, $f(x) = g((x - x^*)^\mathrm{T} H (x - x^*))$, where $g:\mathbb{R}\to\mathbb{R}$ is a strictly increasing function, $H$ is a positive-definite symmetric matrix, and $x^* \in \mathbb{R}^d$ is the optimal solution of $f$. The convergence rate, that is, the decrease rate of the distance from a search point $m_t$ to the optimal solution $x^*$, is proven to be in $O(\exp( - L / \mathrm{Tr}(H) ))$, where $L$ is the smallest eigenvalue of $H$ and $\mathrm{Tr}(H)$ is the trace of $H$. This result generalizes the known rate of $O(\exp(- 1/d ))$ for the case of $H = I_{d}$ ($I_d$ is the identity matrix of dimension $d$) and $O(\exp(- 1/ (d\cdot\xi) ))$ for the case of $H = \mathrm{diag}(\xi \cdot I_{d/2}, I_{d/2})$. To the best of our knowledge, this is the first study in which the convergence rate of the (1+1)-ES is derived explicitly and rigorously on a general convex quadratic function, which depicts the impact of the distribution of the eigenvalues in the Hessian $H$ on the optimization and not only the impact of the condition number of $H$., Comment: 17 pages

Hyperparameter optimization (HPO), formulated as black-box optimization (BBO), is recognized as essential for automation and high performance of machine learning approaches. The CMA-ES is a promising BBO approach with a high degree of parallelism, and has been applied to HPO tasks, often under parallel implementation, and shown superior performance to other approaches including Bayesian optimization (BO). However, if the budget of hyperparameter evaluations is severely limited, which is often the case for end users who do not deserve parallel computing, the CMA-ES exhausts the budget without improving the performance due to its long adaptation phase, resulting in being outperformed by BO approaches. To address this issue, we propose to transfer prior knowledge on similar HPO tasks through the initialization of the CMA-ES, leading to significantly shortening the adaptation time. The knowledge transfer is designed based on the novel definition of task similarity, with which the correlation of the performance of the proposed approach is confirmed on synthetic problems. The proposed warm starting CMA-ES, called WS-CMA-ES, is applied to different HPO tasks where some prior knowledge is available, showing its superior performance over the original CMA-ES as well as BO approaches with or without using the prior knowledge., Comment: accepted at AAAI2021

Neural architecture search (NAS) is an approach for automatically designing a neural network architecture without human effort or expert knowledge. However, the high computational cost of NAS limits its use in commercial applications. Two recent NAS paradigms, namely one-shot and sparse propagation, which reduce the time and space complexities, respectively, provide clues for solving this problem. In this paper, we propose a novel search strategy for one-shot and sparse propagation NAS, namely AdvantageNAS, which further reduces the time complexity of NAS by reducing the number of search iterations. AdvantageNAS is a gradient-based approach that improves the search efficiency by introducing credit assignment in gradient estimation for architecture updates. Experiments on the NAS-Bench-201 and PTB dataset show that AdvantageNAS discovers an architecture with higher performance under a limited time budget compared to existing sparse propagation NAS. To further reveal the reliabilities of AdvantageNAS, we investigate it theoretically and find that it monotonically improves the expected loss and thus converges., Comment: The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)

Evolution strategies (ESs) are zeroth-order stochastic black-box optimization heuristics invariant to monotonic transformations of the objective function. They evolve a multivariate normal distribution, from which candidate solutions are generated. Among different variants, CMA-ES is nowadays recognized as one of the state-of-the-art zeroth-order optimizers for difficult problems. Albeit ample empirical evidence that ESs with a step-size control mechanism converge linearly, theoretical guarantees of linear convergence of ESs have been established only on limited classes of functions. In particular, theoretical results on convex functions are missing, where zeroth-order and also first-order optimization methods are often analyzed. In this paper, we establish almost sure linear convergence and a bound on the expected hitting time of an \new{ES family, namely the $(1+1)_\kappa$-ES, which includes the (1+1)-ES with (generalized) one-fifth success rule} and an abstract covariance matrix adaptation with bounded condition number, on a broad class of functions. The analysis holds for monotonic transformations of positively homogeneous functions and of quadratically bounded functions, the latter of which particularly includes monotonic transformation of strongly convex functions with Lipschitz continuous gradient. As far as the authors know, this is the first work that proves linear convergence of ES on such a broad class of functions., Comment: SIAM Journal on Optimization (Accepted)

Statistically significant patterns mining (SSPM) is an essential and challenging data mining task in the field of knowledge discovery in databases (KDD), in which each pattern is evaluated via a hypothesis test. Our study aims to introduce a preference relation into patterns and to discover the most preferred patterns under the constraint of statistical significance, which has never been considered in existing SSPM problems. We propose an iterative multiple testing procedure that can alternately reject a hypothesis and safely ignore the hypotheses that are less useful than the rejected hypothesis. One advantage of filtering out patterns with low utility is that it avoids consumption of the significance budget by rejection of useless (that is, uninteresting) patterns. This allows the significance budget to be focused on useful patterns, leading to more useful discoveries. We show that the proposed method can control the familywise error rate (FWER) under certain assumptions, that can be satisfied by a realistic problem class in SSPM.\@We also show that the proposed method always discovers a set of patterns that is at least equally or more useful than those discovered using the standard Tarone-Bonferroni method SSPM.\@Finally, we conducted several experiments with both synthetic and real-world data to evaluate the performance of our method. As a result, in the experiments with real-world datasets, the proposed method discovered a larger number of more useful patterns than the existing method for all five conducted tasks., Comment: Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '20), August 23--27, 2020, Virtual Event, CA, USA

In adversarial attacks intended to confound deep learning models, most studies have focused on limiting the magnitude of the modification so that humans do not notice the attack. On the other hand, during an attack against autonomous cars, for example, most drivers would not find it strange if a small insect image were placed on a stop sign, or they may overlook it. In this paper, we present a systematic approach to generate natural adversarial examples against classification models by employing such natural-appearing perturbations that imitate a certain object or signal. We first show the feasibility of this approach in an attack against an image classifier by employing generative adversarial networks that produce image patches that have the appearance of a natural object to fool the target model. We also introduce an algorithm to optimize placement of the perturbation in accordance with the input image, which makes the generation of adversarial examples fast and likely to succeed. Moreover, we experimentally show that the proposed approach can be extended to the audio domain, for example, to generate perturbations that sound like the chirping of birds to fool a speech classifier., Comment: Accepted by AAAI 2020

High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them out-of-the-box to their own problems, albeit its purpose is to automate a part of tuning process. Aiming at a fast, robust, and widely-applicable NAS, we develop a generic optimization framework for NAS. We turn a coupled optimization of connection weights and neural architecture into a differentiable optimization by means of stochastic relaxation. It accepts arbitrary search space (widely-applicable) and enables to employ a gradient-based simultaneous optimization of weights and architecture (fast). We propose a stochastic natural gradient method with an adaptive step-size mechanism built upon our theoretical investigation (robust). Despite its simplicity and no problem-dependent parameter tuning, our method exhibited near state-of-the-art performances with low computational budgets both on image classification and inpainting tasks., Comment: Accepted to ICML 2019. Code is available at https://github.com/shirakawas/ASNG-NAS

We introduce an acceleration for covariance matrix adaptation evolution strategies (CMA-ES) by means of adaptive diagonal decoding (dd-CMA). This diagonal acceleration endows the default CMA-ES with the advantages of separable CMA-ES without inheriting its drawbacks. Technically, we introduce a diagonal matrix D that expresses coordinate-wise variances of the sampling distribution in DCD form. The diagonal matrix can learn a rescaling of the problem in the coordinates within linear number of function evaluations. Diagonal decoding can also exploit separability of the problem, but, crucially, does not compromise the performance on non-separable problems. The latter is accomplished by modulating the learning rate for the diagonal matrix based on the condition number of the underlying correlation matrix. dd-CMA-ES not only combines the advantages of default and separable CMA-ES, but may achieve overadditive speedup: it improves the performance, and even the scaling, of the better of default and separable CMA-ES on classes of non-separable test functions that reflect, arguably, a landscape feature commonly observed in practice. The paper makes two further secondary contributions: we introduce two different approaches to guarantee positive definiteness of the covariance matrix with active CMA, which is valuable in particular with large population size; we revise the default parameter setting in CMA-ES, proposing accelerated settings in particular for large dimension. All our contributions can be viewed as independent improvements of CMA-ES, yet they are also complementary and can be seamlessly combined. In numerical experiments with dd-CMA-ES up to dimension 5120, we observe remarkable improvements over the original covariance matrix adaptation on functions with coordinate-wise ill-conditioning. The improvement is observed also for large population sizes up to about dimension squared., Comment: accepted in Evolutionary Computation Journal (MIT Press)

We consider stochastic algorithms derived from methods for solving deterministic optimization problems, especially comparison-based algorithms derived from stochastic approximation algorithms with a constant step-size. We develop a methodology for proving geometric convergence of the parameter sequence $\{\theta_n\}_{n\geq 0}$ of such algorithms. We employ the ordinary differential equation (ODE) method, which relates a stochastic algorithm to its mean ODE, along with a Lyapunov-like function $\Psi$ such that the geometric convergence of $\Psi(\theta_n)$ implies -- in the case of an optimization algorithm -- the geometric convergence of the expected distance between the optimum and the search point generated by the algorithm. We provide two sufficient conditions for $\Psi(\theta_n)$ to decrease at a geometric rate: $\Psi$ should decrease "exponentially" along the solution to the mean ODE, and the deviation between the stochastic algorithm and the ODE solution (measured by $\Psi$) should be bounded by $\Psi(\theta_n)$ times a constant. We also provide practical conditions under which the two sufficient conditions may be verified easily without knowing the solution of the mean ODE. Our results are any-time bounds on $\Psi(\theta_n)$, so we can deduce not only the asymptotic upper bound on the convergence rate, but also the first hitting time of the algorithm. The main results are applied to a comparison-based stochastic algorithm with a constant step-size for optimization on continuous domains., Comment: Accepted for Stochastic Processes and their Applications

We propose a novel constraint-handling technique for the covariance matrix adaptation evolution strategy (CMA-ES). The proposed technique is aimed at solving explicitly constrained black-box continuous optimization problems, in which the explicit constraint is a constraint whereby the computational time for the constraint violation and its (numerical) gradient are negligible compared to that for the objective function. This method is designed to realize two invariance properties: invariance to the affine transformation of the search space, and invariance to the increasing transformation of the objective and constraint functions. The CMA-ES is designed to possess these properties for handling difficulties that appear in black-box optimization problems, such as non-separability, ill-conditioning, ruggedness, and the different orders of magnitude in the objective. The proposed constraint-handling technique (CHT), known as ARCH, modifies the underlying CMA-ES only in terms of the ranking of the candidate solutions. It employs a repair operator and an adaptive ranking aggregation strategy to compute the ranking. We developed test problems to evaluate the effects of the invariance properties, and performed experiments to empirically verify the invariance of the algorithm. We compared the proposed method with other CHTs on the CEC 2006 constrained optimization benchmark suite to demonstrate its efficacy. Empirical studies reveal that ARCH is able to exploit the explicitness of the constraint functions effectively, sometimes even more efficiently than an existing box-constraint handling technique on box-constrained problems, while exhibiting the invariance properties. Moreover, ARCH overwhelmingly outperforms CHTs by not exploiting the explicit constraints in terms of the number of objective function calls., Comment: Accepted to Evolutionary Computation (MIT Press)

In this study, we propose a new methodology to control how user's data is recognized and used by AI via exploiting the properties of adversarial examples. For this purpose, we propose reversible adversarial example (RAE), a new type of adversarial example. A remarkable feature of RAE is that the image can be correctly recognized and used by the AI model specified by the user because the authorized AI can recover the original image from the RAE exactly by eliminating adversarial perturbation. On the other hand, other unauthorized AI models cannot recognize it correctly because it functions as an adversarial example. Moreover, RAE can be considered as one type of encryption to computer vision since reversibility guarantees the decryption. To realize RAE, we combine three technologies, adversarial example, reversible data hiding for exact recovery of adversarial perturbation, and encryption for selective control of AIs who can remove adversarial perturbation. Experimental results show that the proposed method can achieve comparable attack ability with the corresponding adversarial attack method and similar visual quality with the original image, including white-box attacks and black-box attacks., Comment: arXiv admin note: text overlap with arXiv:1806.09186

Black box discrete optimization (BBDO) appears in wide range of engineering tasks. Evolutionary or other BBDO approaches have been applied, aiming at automating necessary tuning of system parameters, such as hyper parameter tuning of machine learning based systems when being installed for a specific task. However, automation is often jeopardized by the need of strategy parameter tuning for BBDO algorithms. An expert with the domain knowledge must undergo time-consuming strategy parameter tuning. This paper proposes a parameterless BBDO algorithm based on information geometric optimization, a recent framework for black box optimization using stochastic natural gradient. Inspired by some theoretical implications, we develop an adaptation mechanism for strategy parameters of the stochastic natural gradient method for discrete search domains. The proposed algorithm is evaluated on commonly used test problems. It is further extended to two examples of simultaneous optimization of the hyper parameters and the connection weights of deep learning models, leading to a faster optimization than the existing approaches without any effort of parameter tuning.

In this paper we propose a technique to reduce the number of function evaluations, which is often the bottleneck of the black-box optimization, in the information geometric optimization (IGO) that is a generic framework of the probability model-based black-box optimization algorithms and generalizes several well-known evolutionary algorithms, such as the population-based incremental learning (PBIL) and the pure rank-$\mu$ update covariance matrix adaptation evolution strategy (CMA-ES). In each iteration, the IGO algorithms update the parameters of the probability distribution to the natural gradient direction estimated by Monte-Carlo with the samples drawn from the current distribution. Our strategy is to reuse previously generated and evaluated samples based on the importance sampling. It is a technique to reduce the estimation variance without introducing a bias in Monte-Carlo estimation. We apply the sample reuse technique to the PBIL and the pure rank-$\mu$ update CMA-ES and empirically investigate its effect. The experimental results show that the sample reuse helps to reduce the number of function evaluations on many benchmark functions for both the PBIL and the pure rank-$\mu$ update CMA-ES. Moreover, we demonstrate how to combine the importance sampling technique with a variant of the CMA-ES involving an algorithmic component that is not derived in the IGO framework., Comment: 24 pages

This paper explores the use of the standard approach for proving runtime bounds in discrete domains---often referred to as drift analysis---in the context of optimization on a continuous domain. Using this framework we analyze the (1+1) Evolution Strategy with one-fifth success rule on the sphere function. To deal with potential functions that are not lower-bounded, we formulate novel drift theorems. We then use the theorems to prove bounds on the expected hitting time to reach a certain target fitness in finite dimension $d$. The bounds are akin to linear convergence. We then study the dependency of the different terms on $d$ proving a convergence rate dependency of $\Theta(1/d)$. Our results constitute the first non-asymptotic analysis for the algorithm considered as well as the first explicit application of drift analysis to a randomized search heuristic with continuous domain.

Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the appropriate network structure for a target problem is a challenging task. In this paper, we propose a method to simultaneously optimize the network structure and weight parameters during neural network training. We consider a probability distribution that generates network structures, and optimize the parameters of the distribution instead of directly optimizing the network structure. The proposed method can apply to the various network structure optimization problems under the same framework. We apply the proposed method to several structure optimization problems such as selection of layers, selection of unit types, and selection of connections using the MNIST, CIFAR-10, and CIFAR-100 datasets. The experimental results show that the proposed method can find the appropriate and competitive network structures., Comment: To appear in the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18), 9 pages