Search

A significant theoretical advantage of high-order optimization methods is their superior convergence guarantees. For instance, third-order regularized methods reach an $(\epsilon _1,\epsilon _2,\epsilon _3)$third-order critical point in at most ${\mathcal {O}} (\max (\epsilon _1^{-4/3}, \epsilon _2^{-2}, \epsilon _3^{-4} ) )$ iterations. However, the cost of computing high-order derivatives is prohibitively expensive in real applications, including for instance many real-world machine learning tasks. In order to address this problem, we present a sub-sampled optimization method that uses a third-order regularized model to find local minima of smooth and potentially nonconvex objective functions with a finite-sum structure. This algorithm uses sub-sampled derivatives instead of exact quantities and is guaranteed to converge to a third-order critical point. Our analysis relies on a novel tensor concentration inequality for sums of tensors of any order that makes explicit use of the finite-sum structure of the objective function.

We present a full forward-modeled $w$CDM analysis of the KiDS-1000 weak lensing maps using graph-convolutional neural networks (GCNN). Utilizing the $\texttt{CosmoGrid}$, a novel massive simulation suite spanning six different cosmological parameters, we generate almost one million tomographic mock surveys on the sphere. Due to the large data set size and survey area, we perform a spherical analysis while limiting our map resolution to $\texttt{HEALPix}$ $n_\mathrm{side}=512$. We marginalize over systematics such as photometric redshift errors, multiplicative calibration and additive shear bias. Furthermore, we use a map-level implementation of the non-linear intrinsic alignment model along with a novel treatment of baryonic feedback to incorporate additional astrophysical nuisance parameters. We also perform a spherical power spectrum analysis for comparison. The constraints of the cosmological parameters are generated using a likelihood free inference method called Gaussian Process Approximate Bayesian Computation (GPABC). Finally, we check that our pipeline is robust against choices of the simulation parameters. We find constraints on the degeneracy parameter of $S_8 \equiv \sigma_8\sqrt{\Omega_M/0.3} = 0.78^{+0.06}_{-0.06}$ for our power spectrum analysis and $S_8 = 0.79^{+0.05}_{-0.05}$ for our GCNN analysis, improving the former by 16%. This is consistent with earlier analyses of the 2-point function, albeit slightly higher. Baryonic corrections generally broaden the constraints on the degeneracy parameter by about 10%. These results offer great prospects for full machine learning based analyses of on-going and future weak lensing surveys., Comment: 22 pages, 13 figures

The $d$-dimensional Ornstein--Uhlenbeck process (OUP) describes the trajectory of a particle in a $d$-dimensional, spherically symmetric, quadratic potential. The OUP is composed of a drift term weighted by a constant $\theta \geq 0$ and a diffusion coefficient weighted by $\sigma > 0$. In the absence of drift (i.e. $\theta = 0$), the OUP simply becomes a standard Brownian motion (BM). This paper is concerned with estimating the mean first-exit time (MFET) of the OUP from a ball of finite radius $L$ for large $d \gg 0$. We prove that, asymptotically for $d \to \infty$, the OUP takes (on average) no longer to exit than BM. In other words, the mean-reverting drift of the OUP (scaled by $\theta \geq 0$) has asymptotically no effect on its MFET. This finding might be surprising because, for small $d \in \mathbb{N}$, the OUP exit time is significantly larger than BM by a margin that depends on $\theta$. As it allows for the drift to be ignored, it might simplify the analysis of high-dimensional exit-time problems in numerous areas. Finally, our short proof for the non-asymptotic MFET of OUP, using the Andronov--Vitt--Pontryagin formula, might be of independent interest., Comment: 14 pages, 3 figures

We study the theoretical convergence properties of random-search methods when optimizing non-convex objective functions without having access to derivatives. We prove that standard random-search methods that do not rely on second-order information converge to a second-order stationary point. However, they suffer from an exponential complexity in terms of the input dimension of the problem. In order to address this issue, we propose a novel variant of random search that exploits negative curvature by only relying on function evaluations. We prove that this approach converges to a second-order stationary point at a much faster rate than vanilla methods: namely, the complexity in terms of the number of function evaluations is only linear in the problem dimension. We test our algorithm empirically and find good agreements with our theoretical results.

Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle pose and appearance, enable downstream applications in computer graphics, and improve the ability of generative models to understand the concept of image formation. Although there has been prior work on learning such models from collections of 2D images, these approaches require a delicate pose estimation step that exploits annotated keypoints, thereby restricting their applicability to a few specific datasets. In this work, we propose a GAN framework for generating textured triangle meshes without relying on such annotations. We show that the performance of our approach is on par with prior work that relies on ground-truth keypoints, and more importantly, we demonstrate the generality of our method by setting new baselines on a larger set of categories from ImageNet - for which keypoints are not available - without any class-specific hyperparameter tuning. We release our code at https://github.com/dariopavllo/textured-3d-gan, Comment: ICCV 2021

The ability to obtain reliable point estimates of model parameters is of crucial importance in many fields of physics. This is often a difficult task given that the observed data can have a very high number of dimensions. In order to address this problem, we propose a novel approach to construct parameter estimators with a quantifiable bias using an order expansion of highly compressed deep summary statistics of the observed data. These summary statistics are learned automatically using an information maximising loss. Given an observation, we further show how one can use the constructed estimators to obtain approximate Bayes computation (ABC) posterior estimates and their corresponding uncertainties that can be used for parameter inference using Gaussian process regression even if the likelihood is not tractable. We validate our method with an application to the problem of cosmological parameter inference of weak lensing mass maps. We show in that case that the constructed estimators are unbiased and have an almost optimal variance, while the posterior distribution obtained with the Gaussian process regression is close to the true posterior and performs better or equally well than comparable methods., Comment: 18 pages, 10 figures

International audience; Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization are used. We here investigate this phenomenon by revisiting the connection between random initialization in deep networks and spectral instabilities in products of random matrices. Given the rich literature on random matrices, it is not surprising to find that the rank of the intermediate representations in unnormalized networks collapses quickly with depth. In this work we highlight the fact that batch normalization is an effective strategy to avoid rank collapse for both linear and ReLU networks. Leveraging tools from Markov chain theory, we derive a meaningful lower rank bound in deep linear networks. Empirically, we also demonstrate that this rank robustness generalizes to ReLU nets. Finally, we conduct an extensive set of experiments on real-world data sets, which confirm that rank stability is indeed a crucial condition for training modern-day deep neural architectures.

Fault-tolerant quantum computers offer the promise of dramatically improving machine learning through speed-ups in computation or improved model scalability. In the near-term, however, the benefits of quantum machine learning are not so clear. Understanding expressibility and trainability of quantum models-and quantum neural networks in particular-requires further investigation. In this work, we use tools from information geometry to define a notion of expressibility for quantum and classical models. The effective dimension, which depends on the Fisher information, is used to prove a novel generalisation bound and establish a robust measure of expressibility. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks. To then assess the trainability of quantum models, we connect the Fisher information spectrum to barren plateaus, the problem of vanishing gradients. Importantly, certain quantum neural networks can show resilience to this phenomenon and train faster than classical models due to their favourable optimisation landscapes, captured by a more evenly spread Fisher information spectrum. Our work is the first to demonstrate that well-designed quantum neural networks offer an advantage over classical neural networks through a higher effective dimension and faster training ability, which we verify on real quantum hardware., 25 pages, 10 figures

Derivative-free optimization (DFO) has recently gained a lot of momentum in machine learning, spawning interest in the community to design faster methods for problems where gradients are not accessible. While some attention has been given to the concept of acceleration in the DFO literature, existing stochastic algorithms for objective functions with a finite-sum structure have not been shown theoretically to achieve an accelerated rate of convergence. Algorithms that use acceleration in such a setting are prone to instabilities, making it difficult to reach convergence. In this work, we exploit the finite-sum structure of the objective in order to design a variance-reduced DFO algorithm that provably yields acceleration. We prove rates of convergence for both smooth convex and strongly-convex finite-sum objective functions. Finally, we validate our theoretical results empirically on several tasks and datasets., 48 pages, 44 figures; Proceedings of the 37th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020

We study preconditioned gradient-based optimization methods where the preconditioning matrix has block-diagonal form. Such a structural constraint comes with the advantage that the update computation is block-separable and can be parallelized across multiple independent tasks. Our main contribution is to demonstrate that the convergence of these methods can significantly be improved by a randomization technique which corresponds to repartitioning coordinates across tasks during the optimization procedure. We provide a theoretical analysis that accurately characterizes the expected convergence gains of repartitioning and validate our findings empirically on various traditional machine learning tasks. From an implementation perspective, block-separable models are well suited for parallelization and, when shared memory is available, randomization can be implemented on top of existing methods very efficiently to improve convergence., improvement in Theorem 3 compared to ICML 2020 version

This study deals with semantic segmentation of high-resolution (aerial) images where a semantic class label is assigned to each pixel via supervised classification as a basis for automatic map generation. Recently, deep convolutional neural networks (CNNs) have shown impressive performance and have quickly become the de-facto standard for semantic segmentation, with the added benefit that task-specific feature design is no longer necessary. However, a major downside of deep learning methods is that they are extremely data-hungry, thus aggravating the perennial bottleneck of supervised classification, to obtain enough annotated training data. On the other hand, it has been observed that they are rather robust against noise in the training labels. This opens up the intriguing possibility to avoid annotating huge amounts of training data, and instead train the classifier from existing legacy data or crowd-sourced maps which can exhibit high levels of noise. The question addressed in this paper is: can training with large-scale, publicly available labels replace a substantial part of the manual labeling effort and still achieve sufficient performance? Such data will inevitably contain a significant portion of errors, but in return virtually unlimited quantities of it are available in larger parts of the world. We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled, pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations. We report our results that indicate that satisfying performance can be obtained with significantly less manual annotation effort, by exploiting noisy large-scale training data., Comment: Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

This work presents a novel realization approach to quantum Boltzmann machines (QBMs). The preparation of the required Gibbs states, as well as the evaluation of the loss function’s analytic gradient, is based on variational quantum imaginary time evolution, a technique that is typically used for ground-state computation. In contrast to existing methods, this implementation facilitates near-term compatible QBM training with gradients of the actual loss function for arbitrary parameterized Hamiltonians which do not necessarily have to be fully visible but may also include hidden units. The variational Gibbs state approximation is demonstrated with numerical simulations and experiments run on real quantum hardware provided by IBM Quantum. Furthermore, we illustrate the application of this variational QBM approach to generative and discriminative learning tasks using numerical simulation., Quantum Machine Intelligence, 3 (1)

Learning system dynamics directly from observations is a promising direction in machine learning due to its potential to significantly enhance our ability to understand physical systems. However, the dynamics of many real-world systems are challenging to learn due to the presence of nonlinear potentials and a number of interactions that scales quadratically with the number of particles $N$, as in the case of the N-body problem. In this work, we introduce an approach that transforms a fully-connected interaction graph into a hierarchical one which reduces the number of edges to $O(N)$. This results in linear time and space complexity while the pre-computation of the hierarchical graph requires $O(N\log (N))$ time and $O(N)$ space. Using our approach, we are able to train models on much larger particle counts, even on a single GPU. We evaluate how the phase space position accuracy and energy conservation depend on the number of simulated particles. Our approach retains high accuracy and efficiency even on large-scale gravitational N-body simulations which are impossible to run on a single machine if a fully-connected graph is used. Similar results are also observed when simulating Coulomb interactions. Furthermore, we make several important observations regarding the performance of this new hierarchical model, including: i) its accuracy tends to improve with the number of particles in the simulation and ii) its generalisation to unseen particle counts is also much better than for models that use all $O(N^2)$ interactions., Comment: 19 pages, 20 figures, AAAI 2021

We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene. We exploit sparse semantic maps to control object shapes and classes, as well as textual descriptions or attributes to control both local and global style. In order to condition our model on textual descriptions, we introduce a semantic attention module whose computational cost is independent of the image resolution. To further augment the controllability of the scene, we propose a two-step generation scheme that decomposes background and foreground. The label maps used to train our model are produced by a large-vocabulary object detector, which enables access to unlabeled data and provides structured instance information. In such a setting, we report better FID scores compared to fully-supervised settings where the model is trained on ground-truth semantic maps. We also showcase the ability of our model to manipulate a scene on complex datasets such as COCO and Visual Genome., European Conference on Computer Vision (ECCV) 2020, Spotlight. Code at https://github.com/dariopavllo/style-semantics

Convolutional Neural Networks (CNN) have recently been demonstrated on synthetic data to improve upon the precision of cosmological inference. In particular they have the potential to yield more precise cosmological constraints from weak lensing mass maps than the two-point functions. We present the cosmological results with a CNN from the KiDS-450 tomographic weak lensing dataset, constraining the total matter density $\Omega_m$, the fluctuation amplitude $\sigma_8$, and the intrinsic alignment amplitude $A_{\rm{IA}}$. We use a grid of N-body simulations to generate a training set of tomographic weak lensing maps. We test the robustness of the expected constraints to various effects, such as baryonic feedback, simulation accuracy, different value of $H_0$, or the lightcone projection technique. We train a set of ResNet-based CNNs with varying depths to analyze sets of tomographic KiDS mass maps divided into 20 flat regions, with applied Gaussian smoothing of $\sigma=2.34$ arcmin. The uncertainties on shear calibration and $n(z)$ error are marginalized in the likelihood pipeline. Following a blinding scheme, we derive constraints of $S_8 = \sigma_8 (\Omega_m/0.3)^{0.5} = 0.777^{+0.038}_{-0.036}$ with our CNN analysis, with $A_{\rm{IA}}=1.398^{+0.779}_{-0.724}$. We compare this result to the power spectrum analysis on the same maps and likelihood pipeline and find an improvement of about $30\%$ for the CNN. We discuss how our results offer excellent prospects for the use of deep learning in future cosmological data analysis., Comment: 22 pages, 15 figures

The choice of how to retain information about past gradients dramatically affects the convergence properties of state-of-the-art stochastic optimization methods, such as Heavy-ball, Nesterov's momentum, RMSprop and Adam. Building on this observation, we use stochastic differential equations (SDEs) to explicitly study the role of memory in gradient-based algorithms. We first derive a general continuous-time model that can incorporate arbitrary types of memory, for both deterministic and stochastic settings. We provide convergence guarantees for this SDE for weakly-quasi-convex and quadratically growing functions. We then demonstrate how to discretize this SDE to get a flexible discrete-time algorithm that can implement a board spectrum of memories ranging from short- to long-term. Not only does this algorithm increase the degrees of freedom in algorithmic choice for practitioners but it also comes with better stability properties than classical momentum in the convex stochastic setting. In particular, no iterate averaging is needed for convergence. Interestingly, our analysis also provides a novel interpretation of Nesterov's momentum as stable gradient amplification and highlights a possible reason for its unstable behavior in the (convex) stochastic setting. Furthermore, we discuss the use of long term memory for second-moment estimation in adaptive methods, such as Adam and RMSprop. Finally, we provide an extensive experimental study of the effect of different types of memory in both convex and nonconvex settings., Accepted paper at the 35th Conference on Uncertainty in Artificial Intelligence (UAI), Tel Aviv, 2019

Quantum algorithms have the potential to outperform their classical counterparts in a variety of tasks. The realization of the advantage often requires the ability to load classical data efficiently into quantum states. However, the best known methods require O(2n) gates to load an exact representation of a generic data structure into an n-qubit state. This scaling can easily predominate the complexity of a quantum algorithm and, thereby, impair potential quantum advantage. Our work presents a hybrid quantum-classical algorithm for efficient, approximate quantum state loading. More precisely, we use quantum Generative Adversarial Networks (qGANs) to facilitate efficient learning and loading of generic probability distributions - implicitly given by data samples - into quantum states. Through the interplay of a quantum channel, such as a variational quantum circuit, and a classical neural network, the qGAN can learn a representation of the probability distribution underlying the data samples and load it into a quantum state. The loading requires O(poly(n)) gates and can thus enable the use of potentially advantageous quantum algorithms, such as Quantum Amplitude Estimation. We implement the qGAN distribution learning and loading method with Qiskit and test it using a quantum simulation as well as actual quantum processors provided by the IBM Q Experience. Furthermore, we employ quantum simulation to demonstrate the use of the trained quantum channel in a quantum finance application., npj Quantum Information, 5, ISSN:2056-6387

Proceedings of Machine Learning Research, 89, ISSN:2640-3498, Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019)

Ordinary differential equation (ODE) models of gradient-based optimization methods can provide insights into the dynamics of learning and inspire the design of new algorithms. Unfortunately, this thought-provoking perspective is weakened by the fact that, in the worst case, the error between the algorithm steps and its ODE approximation grows exponentially with the number of iterations. In an attempt to encourage the use of continuous-time methods in optimization, we show that, if some additional regularity on the objective is assumed, the ODE representations of Gradient Descent and Heavy-ball do not suffer from the aforementioned problem, once we allow for a small perturbation on the algorithm initial condition. In the dynamical systems literature, this phenomenon is called shadowing. Our analysis relies on the concept of hyperbolicity, as well as on tools from numerical analysis.

Generative Adversarial Networks (GANs) have shown remarkable results in modeling complex distributions, but their evaluation remains an unsettled issue. Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training. The latter cannot be determined by simply inspecting the generator and discriminator loss curves as they behave non-intuitively. We leverage the notion of duality gap from game theory to propose a measure that addresses both (i) and (ii) at a low computational cost. Extensive experiments show the effectiveness of this measure to rank different GAN models and capture the typical GAN failure scenarios, including mode collapse and non-convergent behaviours. This evaluation metric also provides meaningful monitoring on the progression of the loss during training. It highly correlates with FID on natural image datasets, and with domain specific scores for text, sound and cosmology data where FID is not directly suitable. In particular, our proposed metric requires no labels or a pretrained classifier, making it domain agnostic.

We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions. Furthermore, we show that - contrary to the case of isotropic noise - this variance is proportional to the magnitude of the corresponding eigenvalues and not decreasing in the dimensionality. Based upon this observation we propose a new assumption under which we show that the injection of explicit, isotropic noise usually applied to make gradient descent escape saddle points can successfully be replaced by a simple SGD step. Additionally - and under the same condition - we derive the first convergence rate for plain SGD to a second-order stationary point in a number of iterations that is independent of the problem dimension.

Modeling the Point Spread Function (PSF) of wide-field surveys is vital for many astrophysical applications and cosmological probes including weak gravitational lensing. The PSF smears the image of any recorded object and therefore needs to be taken into account when inferring properties of galaxies from astronomical images. In the case of cosmic shear, the PSF is one of the dominant sources of systematic errors and must be treated carefully to avoid biases in cosmological parameters. Recently, forward modeling approaches to calibrate shear measurements within the Monte-Carlo Control Loops ($MCCL$) framework have been developed. These methods typically require simulating a large amount of wide-field images, thus, the simulations need to be very fast yet have realistic properties in key features such as the PSF pattern. Hence, such forward modeling approaches require a very flexible PSF model, which is quick to evaluate and whose parameters can be estimated reliably from survey data. We present a PSF model that meets these requirements based on a fast deep-learning method to estimate its free parameters. We demonstrate our approach on publicly available SDSS data. We extract the most important features of the SDSS sample via principal component analysis. Next, we construct our model based on perturbations of a fixed base profile, ensuring that it captures these features. We then train a Convolutional Neural Network to estimate the free parameters of the model from noisy images of the PSF. This allows us to render a model image of each star, which we compare to the SDSS stars to evaluate the performance of our method. We find that our approach is able to accurately reproduce the SDSS PSF at the pixel level, which, due to the speed of both the model evaluation and the parameter estimation, offers good prospects for incorporating our method into the $MCCL$ framework., 25 pages, 8 figures, 1 table

Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years. While first-order methods seem to dominate the field, second-order methods are nevertheless attractive as they potentially require fewer communication rounds to converge. However, there are significant drawbacks that impede their wide adoption, such as the computation and the communication of a large Hessian matrix. In this paper we present a new algorithm for distributed training of generalized linear models that only requires the computation of diagonal blocks of the Hessian matrix on the individual workers. To deal with this approximate information we propose an adaptive approach that - akin to trust-region methods - dynamically adapts the auxiliary model to compensate for modeling errors. We provide theoretical rates of convergence for a wide class of problems including L1-regularized objectives. We also demonstrate that our approach achieves state-of-the-art results on multiple large benchmark datasets., Comment: appearing at ICML 2018 - Proceedings of the 35th International Conference on Machine Learning, Stockholm, Schweden, PMLR 80, 2018

We propose a new approach, named PolyMapper, to circumvent the conventional pixel-wise segmentation of (aerial) images and predict objects in a vector representation directly. PolyMapper directly extracts the topological map of a city from overhead images as collections of building footprints and road networks. In order to unify the shape representation for different types of objects, we also propose a novel sequentialization method that reformulates a graph structure as closed polygons. Experiments are conducted on both existing and self-collected large-scale datasets of several cities. Our empirical results demonstrate that our end-to-end learnable model is capable of drawing polygons of building footprints and road networks that very closely approximate the structure of existing online map services, in a fully automated manner. Quantitative and qualitative comparison to the state-of-the-art also shows that our approach achieves good levels of performance. To the best of our knowledge, the automatic extraction of large-scale topological maps is a novel contribution in the remote sensing community that we believe will help develop models with more informed geometrical constraints., Comment: ICCV 2019

Deep learning is a powerful analysis technique that has recently been proposed as a method to constrain cosmological parameters from weak lensing mass maps. Due to its ability to learn relevant features from the data, it is able to extract more information from the mass maps than the commonly used power spectrum, and thus achieve better precision for cosmological parameter measurement. We explore the advantage of Convolutional Neural Networks (CNN) over the power spectrum for varying levels of shape noise and different smoothing scales applied to the maps. We compare the cosmological constraints from the two methods in the $\Omega_M-\sigma_8$ plane for sets of 400 deg$^2$ convergence maps. We find that, for a shape noise level corresponding to 8.53 galaxies/arcmin$^2$ and the smoothing scale of $\sigma_s = 2.34$ arcmin, the network is able to generate 45% tighter constraints. For smaller smoothing scale of $\sigma_s = 1.17$ the improvement can reach $\sim 50 \%$, while for larger smoothing scale of $\sigma_s = 5.85$, the improvement decreases to 19%. The advantage generally decreases when the noise level and smoothing scales increase. We present a new training strategy to train the neural network with noisy data, as well as considerations for practical applications of the deep learning approach., Comment: 17 pages, 12 figures

Advances in Neural Information Processing Systems 30, ISBN:978-1-5108-6096-4

For many machine learning problems, data is abundant and it may be prohibitive to make multiple passes through the full training set. In this context, we investigate strategies for dynamically increasing the effective sample size, when using iterative methods such as stochastic gradient descent. Our interest is motivated by the rise of variance-reduced methods, which achieve linear convergence rates that scale favorably for smaller sample sizes. Exploiting this feature, we show -- theoretically and empirically -- how to obtain significant speed-ups with a novel algorithm that reaches statistical accuracy on an $n$-sample in $2n$, instead of $n \log n$ steps.

We propose a novel approach for mitigating radio frequency interference (RFI) signals in radio data using the latest advances in deep learning. We employ a special type of Convolutional Neural Network, the U-Net, that enables the classification of clean signal and RFI signatures in 2D time-ordered data acquired from a radio telescope. We train and assess the performance of this network using the HIDE & SEEK radio data simulation and processing packages, as well as early Science Verification data acquired with the 7m single-dish telescope at the Bleien Observatory. We find that our U-Net implementation is showing competitive accuracy to classical RFI mitigation algorithms such as SEEK's SumThreshold implementation. We publish our U-Net software package on GitHub under GPLv3 license., 8 pages, 3 figures Published in Astronomy and Computing. The code is available at https://github.com/jakeret/tf_unet

Many fundamental problems in natural language processing rely on determining what entities appear in a given text. Commonly referenced as entity linking, this step is a fundamental component of many NLP tasks such as text understanding, automatic summarization, semantic search or machine translation. Name ambiguity, word polysemy, context dependencies and a heavy-tailed distribution of entities contribute to the complexity of this problem. We here propose a probabilistic approach that makes use of an effective graphical model to perform collective entity disambiguation. Input mentions (i.e., linkable token spans) are disambiguated jointly across an entire document by combining a document-level prior of entity co-occurrences with local information captured from mentions and their surrounding context. The model is based on simple sufficient statistics extracted from data, thus relying on few parameters to be learned. Our method does not require extensive feature engineering, nor an expensive training procedure. We use loopy belief propagation to perform approximate inference. The low complexity of our model makes this step sufficiently fast for real-time usage. We demonstrate the accuracy of our approach on a wide range of benchmark datasets, showing that it matches, and in many cases outperforms, existing state-of-the-art methods.

Efficient and accurate segmentation of cellular structures in microscopic data is an essential task in medical imaging. Many state-of-the-art approaches to image segmentation use structured models whose parameters must be carefully chosen for optimal performance. A popular choice is to learn them using a large-margin framework and more specifically structured support vector machines (SSVM). Although SSVMs are appealing, they suffer from certain limitations. First, they are restricted in practice to linear kernels because the more powerful non-linear kernels cause the learning to become prohibitively expensive. Second, they require iteratively finding the most violated constraints, which is often intractable for the loopy graphical models used in image segmentation. This requires approximation that can lead to reduced quality of learning. In this article, we propose three novel techniques to overcome these limitations. We first introduce a method to “kernelize” the features so that a linear SSVM framework can leverage the power of non-linear kernels without incurring much additional computational cost. Moreover, we employ a working set of constraints to increase the reliability of approximate subgradient methods and introduce a new way to select a suitable step size at each iteration. We demonstrate the strength of our approach on both 2D and 3D electron microscopic (EM) image data and show consistent performance improvement over state-of-the-art approaches.

Scanning Electron Microscopy (SEM) is an invaluable tool for biologists and neuroscientists to study brain structure at the intracellular level. While able to image tissue samples with up to 5 nm isotropic resolution, image acquisition is prohibitively slow and limits the size of processed samples. In this work, we propose a novel approach to speeding up imaging when looking for specific structures. Unlike earlier methods, we explicitly balance the conflicting requirements of spending enough time scanning potential regions of interest to ensure that all targets are found while not wasting time on unpromising regions. This is achieved by using a Markov Random Field to model target locations and optimizing scanning locations by using a Branch-and-Bound strategy. We show that our approach significantly outperforms state-of-the-art methods to locate mitochondria in brain tissue.

We propose a working set based approximate sub gradient descent algorithm to minimize the margin-sensitive hinge loss arising from the soft constraints in max-margin learning frameworks, such as the structured SVM. We focus on the setting of general graphical models, such as loopy MRFs and CRFs commonly used in image segmentation, where exact inference is intractable and the most violated constraints can only be approximated, voiding the optimality guarantees of the structured SVM's cutting plane algorithm as well as reducing the robustness of existing sub gradient based methods. We show that the proposed method obtains better approximate sub gradients through the use of working sets, leading to improved convergence properties and increased reliability. Furthermore, our method allows new constraints to be randomly sampled instead of computed using the more expensive approximate inference techniques such as belief propagation and graph cuts, which can be used to reduce learning time at only a small cost of performance. We demonstrate the strength of our method empirically on the segmentation of a new publicly available electron microscopy dataset as well as the popular MSRC data set and show state-of-the-art results.

For biologists studying the morphology of cells, electron microscopy (EM) is the method of choice with its nm resolution. However, the time necessary to acquire EM image series is long and often limits both the number and size of samples imaged. This paper presents a strategy for fast imaging and automated selection of regions of interest that significantly accelerates this process. In particular, this strategy involves scanning a tissue sample once, finding regions of interest in which target structures might be located, scanning these regions once again, and iterating the process until only relevant regions of the block face have been scanned repeatedly. For mitochondria and synapses, this approach is shown to produce near equal localization results to current state-of-the art techniques, and does so in almost a tenth of the time.

Scanning Electron Microscopy (SEM) is an invaluable tool for biologists and neuroscientists to study brain structure at the intra- cellular level. While able to image tissue samples with up to 5nm isotropic resolution, image acquisition is prohibitively slow and limits the size of processed samples. In this work, we propose a novel approach to speeding up imaging when looking for specific structures. Unlike earlier methods, we explicitly balance the conflicting requirements of spending enough time scanning potential regions of interest to ensure that all targets are found while not wasting time on unpromising regions. This is achieved by using a Markov Random Field to model target locations and optimiz- ing scanning locations by using a Branch-and-Bound strategy. We show that our approach significantly outperforms state-of-the-art methods to locate mitochondria in brain tissue.

Most state-of-the-art approaches to image segmentation formulate the problem using Conditional Random Fields. These models typically include a unary term and a pairwise term, whose parameters must be carefully chosen for optimal performance. Recently, structured learning approaches such as Structured SVMs (SSVM) have made it possible to jointly learn these model parameters. However, they have been limited to linear kernels, since more powerful non-linear kernels cause the learning to become prohibitively expensive. In this paper, we introduce an approach to ``kernelize'' the features so that a linear SSVM framework can leverage the power of non-linear kernels without incurring the high computational cost. We demonstrate the advantages of this approach in a series of image segmentation experiments on the MSRC data set as well as 2D and 3D datasets containing imagery of neural tissue acquired with electron microscopes.

Many state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accomplished by introducing additional latent variables to the model, which can greatly increase its complexity. As a result, estimating the model parameters or computing the best maximum a posteriori (MAP) assignment becomes a computationally expensive task. In a series of experiments on the PASCAL and the MSRC datasets, we were unable to find evidence of a significant performance increase attributed to the introduction of such constraints. On the contrary, we found that similar levels of performance can be achieved using a much simpler design that essentially ignores these constraints. This more simple approach makes use of the same local and global features to leverage evidence from the image, but instead directly biases the preferences of individual pixels. While our investigation does not prove that spatial and consistency constraints are not useful in principle, it points to the conclusion that they should be validated in a larger context.

It is becoming increasingly clear that mitochondria play an important role in neural function. Recent studies show mitochondrial morphology to be crucial to cellular physiology and synaptic function and a link between mitochondrial defects and neuro-degenerative diseases is strongly suspected. Electron microscopy (EM), with its very high resolution in all three directions, is one of the key tools to look more closely into these issues but the huge amounts of data it produces make automated analysis necessary. State-of-the-art computer vision algorithms designed to operate on natural 2-D images tend to perform poorly when applied to EM data for a number of reasons. First, the sheer size of a typical EM volume renders most modern segmentation schemes intractable. Furthermore, most approaches ignore important shape cues, relying only on local statistics that easily become confused when confronted with noise and textures inherent in the data. Finally, the conventional assumption that strong image gradients always correspond to object boundaries is violated by the clutter of distracting membranes. In this work, we propose an automated graph partitioning scheme that addresses these issues. It reduces the computational complexity by operating on supervoxels instead of voxels, incorporates shape features capable of describing the 3-D shape of the target objects, and learns to recognize the distinctive appearance of true boundaries. Our experiments demonstrate that our approach is able to segment mitochondria at a performance level close to that of a human annotator, and outperforms a state-of-the-art 3-D segmentation technique.

Tabletop systems have become quite popular in recent years, during which there was considerable enthusiasm for the development of new interfaces. In this paper, we establish a comparison between touch and tangible interfaces. We set up an experiment involving several actions like translation and rotation. We recruited 40 participants to take part in a user study and we present our results with a discussion on the design of touch and tangible interfaces. Our contribution is an empirical study showing that overall, the tangible interface is much faster but under certain conditions, the touch interface could gain the upper hand.

This paper describes TinkerSheets, a paper-based interface to tangible simulations. The proposed interface combines the advantages of form-based input and paper. Form-based input allows to set an arbitrary number of parameters. Using paper as a medium for the interface keeps the interaction modality consistently physical. TinkerSheets are also used as an output screen to display summarized information about the simulation. A user study conducted in an authentic context shows how the characteristics of the interface shape real world usage. We also describe how the affordances of this control and visualization interface support the co-design of interaction with end-users.

While there has been substantial progress in segmenting natural im-ages, state-of-the-art methods that perform well in such tasks unfortunately tend to underperform when confronted with the different challenges posed by electron microscope (EM) data. For example, in EM imagery of neural tissue, numerous cells and subcellular structures appear within a single image, they exhibit irregular shapes that cannot be easily modeled by standard techniques, and confusing textures clutter the background. We propose a fully automated approach that handles these challenges by using sophisticated cues that capture global shape and texture information, and by learning the specific appearance of object boundaries. We demonstrate that our approach significantly outperforms state-of-the-art techniques and closely matches the performance of human annotators.

This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual approaches typically require to establish a correspondence to English for which powerful classifiers are already available. In contrast, our method does not require such supervision. We leverage large amounts of weakly- supervised data in various languages to train a multi-layer convolutional network and demonstrate the importance of using pre-training of such networks. We thoroughly evaluate our approach on various multi-lingual datasets, including the recent SemEval-2016 sentiment prediction benchmark (Task 4), where we achieved state-of-the-art performance. We also compare the performance of our model trained individually for each language to a variant trained for all languages at once. We show that the latter model reaches slightly worse - but still acceptable - performance when compared to the single language model, while benefiting from better generalization properties across languages., Proceedings of the 26th International Conference on World Wide Web (WWW' 17)

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.

In this paper, we propose a classifier for predicting message-level sentiments of English micro-blog messages from Twitter. Our method builds upon the convolutional sentence embedding approach proposed by (Severyn and Moschitti, 2015a; Severyn and Moschitti, 2015b). We leverage large amounts of data with distant supervision to train an ensemble of 2-layer convolutional neural networks whose predictions are combined using a random forest classifier. Our approach was evaluated on the datasets of the SemEval-2016 competition (Task 4) outperforming all other approaches for the Message Polarity Classification task.

In this paper, we improve upon earlier approaches to segmenting mitochondria in Electron Microscopy images by explicitly modeling the double membrane that encloses mitochondria, as well as using features that capture context over an extended neighborhood. We demonstrate that this results in both improved classification accuracy and reduced computational requirements for training.

We presented an approach for speeding-up image acquisition when tasked with localizing specific structures in FIB-SEM imagery. It exploits the fact that low-quality images can be acquired faster than higher-quality ones and yet be sufficient for inference purposes. We have demonstrated greater than five-fold speed-ups at very little loss in accuracy in the context of mitochondria and synapse detection. Furthermore, the algorithm we propose is generic and applicable to many imaging modalities that allow trading quality for speed. The disclosed method of data acquisition for an apparatus having a Scanning Electron Microscope (SEM) for microscopic imaging and a Focused Ion Beam (FIB) unit for sample milling comprises the following steps: scanning a sample with the SEM to obtain an image region (I'); analyzing the image region with a classifier function (hi ) that operates on the image region and returns a classification image whose content depends on whether the classifier estimates that a pixel in the image region belongs to a determined target structure or not; searching in the classification image for disjoint regions that indicate potential target locations and adding the regions so found to a list of candidates; iterating the steps of scanning, analyzing and searching on the members of the list of candidates.

Stochastic Gradient Descent (SGD) is a workhorse in machine learning, yet its slow convergence can be a computational bottleneck. Variance reduction techniques such as SAG, SVRG and SAGA have been proposed to overcome this weakness, achieving linear convergence. However, these methods are either based on computations of full gradients at pivot points, or on keeping per data point corrections in memory. Therefore speed-ups relative to SGD may need a minimal number of epochs in order to materialize. This paper investigates algorithms that can exploit neighborhood structure in the training data to share and re-use information about past stochastic gradients across data points, which offers advantages in the transient optimization phase. As a side-product we provide a unified convergence analysis for a family of variance reduction algorithms, which we call memorization algorithms. We provide experimental results supporting our theory., Appears in: Advances in Neural Information Processing Systems 28 (NIPS 2015). 13 pages

While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such models. In this work, we bridge this gap by leveraging recent advances in differentiable rendering. We design a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text. Finally, we propose an evaluation methodology that assesses the mesh and texture quality separately., Comment: NeurIPS 2020, Oral presentation. Code at https://github.com/dariopavllo/convmesh

We propose new continuous-time formulations for first-order stochastic optimization algorithms such as mini-batch gradient descent and variance-reduced methods. We exploit these continuous-time models, together with simple Lyapunov analysis as well as tools from stochastic calculus, in order to derive convergence bounds for various types of non-convex functions. Guided by such analysis, we show that the same Lyapunov arguments hold in discrete-time, leading to matching rates. In addition, we use these models and Ito calculus to infer novel insights on the dynamics of SGD, proving that a decreasing learning rate acts as time warping or, equivalently, as landscape stretching., Advances in Neural Information Processing Systems 32, ISBN:978-1-7138-0793-3