Search

In this work, we deal with the problem of computing a comprehensive front of efficient solutions in multi-objective portfolio optimization problems in presence of sparsity constraints. We start the discussion pointing out some weaknesses of the classical scalarization approach when applied to the considered class of problems. We are then motivated to propose a suitable algorithmic framework that is designed to overcome these limitations: the novel algorithm combines a gradient-based exploration-refinement strategy with a tailored initialization scheme based on memetic or multi-start descent procedures. Thorough computational experiments highlight how the proposed method is far superior to both scalarization and popular genetic algorithms.

Sim-to-real transfer remains a significant challenge in soft robotics due to the unpredictability introduced by common manufacturing processes such as 3D printing and molding. These processes often result in deviations from simulated designs, requiring multiple prototypes before achieving a functional system. In this study, we propose a novel methodology to address these limitations by combining advanced rapid prototyping techniques and an efficient optimization strategy. Firstly, we employ rapid prototyping methods typically used for rigid structures, leveraging their precision to fabricate compliant components with reduced manufacturing errors. Secondly, our optimization framework minimizes the need for extensive prototyping, significantly reducing the iterative design process. The methodology enables the identification of stiffness parameters that are more practical and achievable within current manufacturing capabilities. The proposed approach demonstrates a substantial improvement in the efficiency of prototype development while maintaining the desired performance characteristics. This work represents a step forward in bridging the sim-to-real gap in soft robotics, paving the way towards a faster and more reliable deployment of soft robotic systems.

In this paper we consider bound-constrained mixed-integer optimization problems where the objective function is differentiable w.r.t.\ the continuous variables for every configuration of the integer variables. We mainly suggest to exploit derivative information when possible in these scenarios: concretely, we propose an algorithmic framework that carries out local optimization steps, alternating searches along gradient-based and primitive directions. The algorithm is shown to match the convergence properties of a derivative-free counterpart. Most importantly, the results of thorough computational experiments show that the proposed method clearly outperforms not only the derivative-free approach but also a state-of-the-art solver both in terms of efficiency and effectiveness.

In this manuscript, we address continuous unconstrained multi-objective optimization problems and we discuss descent type methods for the reconstruction of the Pareto set. Specifically, we analyze the class of Front Descent methods, which generalizes the Front Steepest Descent algorithm allowing the employment of suitable, effective search directions (e.g., Newton, Quasi-Newton, Barzilai-Borwein). We provide a deep characterization of the behavior and the mechanisms of the algorithmic framework, and we prove that, under reasonable assumptions, standard convergence results and some complexity bounds hold for the generalized approach. Moreover, we prove that popular search directions can indeed be soundly used within the framework. Then, we provide a completely novel type of convergence results, concerning the sequence of sets produced by the procedure. In particular, iterate sets are shown to asymptotically approach stationarity for all of their points; the convergence result is accompanied by a worst-case iteration complexity bound; additionally, in finite precision settings, the sets are shown to only be enriched through exploration steps in later iterations, and suitable stopping conditions can be devised. Finally, the results from a large experimental benchmark show that the proposed class of approaches far outperforms state-of-the-art methodologies.

In this paper, we propose an extension for semi-supervised Minimum Sum-of-Squares Clustering (MSSC) problems of MDEClust, a memetic framework based on the Differential Evolution paradigm for unsupervised clustering. In semi-supervised MSSC, background knowledge is available in the form of (instance-level) "must-link" and "cannot-link" constraints, each of which indicating if two dataset points should be associated to the same or to a different cluster, respectively. The presence of such constraints makes the problem at least as hard as its unsupervised version and, as a consequence, some framework operations need to be carefully designed to handle this additional complexity: for instance, it is no more true that each point is associated to its nearest cluster center. As far as we know, our new framework, called S-MDEClust, represents the first memetic methodology designed to generate a (hopefully) optimal feasible solution for semi-supervised MSSC problems. Results of thorough computational experiments on a set of well-known as well as synthetic datasets show the effectiveness and efficiency of our proposal.

In this paper, we deal with batch Bayesian Optimization (Bayes-Opt) problems over a box and we propose a novel bi-objective optimization (BOO) acquisition strategy to sample points where to evaluate the objective function. The BOO problem involves the Gaussian Process posterior mean and variance functions, which, in most of the acquisition strategies from the literature, are generally used in combination, frequently through scalarization. However, such scalarization could compromise the Bayes-Opt process performance, as getting the desired trade-off between exploration and exploitation is not trivial in most cases. We instead aim to reconstruct the Pareto front of the BOO problem based on optimizing both the posterior mean as well as the variance, thus generating multiple trade-offs without any a priori knowledge. The reconstruction is performed through the Non-dominated Sorting Memetic Algorithm (NSMA), recently proposed in the literature and proved to be effective in solving hard MOO problems. Finally, we present two clustering approaches, each of them operating on a different space, to select potentially optimal points from the Pareto front. We compare our methodology with well-known acquisition strategies from the literature, showing its effectiveness on a wide set of experiments.

In this paper, we consider multi-objective optimization problems with a sparsity constraint on the vector of variables. For this class of problems, inspired by the homonymous necessary optimality condition for sparse single-objective optimization, we define the concept of L-stationarity and we analyze its relationships with other existing conditions and Pareto optimality concepts. We then propose two novel algorithmic approaches: the first one is an Iterative Hard Thresholding method aiming to find a single L-stationary solution, while the second one is a two-stage algorithm designed to construct an approximation of the whole Pareto front. Both methods are characterized by theoretical properties of convergence to points satisfying necessary conditions for Pareto optimality. Moreover, we report numerical results establishing the practical effectiveness of the proposed methodologies., Comment: 20 pages, 7 figures, 1 table

In this paper, we deal with the Front Steepest Descent algorithm for multi-objective optimization. We point out that the algorithm from the literature is often incapable, by design, of spanning large portions of the Pareto front. We thus introduce some modifications within the algorithm aimed to overcome this significant limitation. We prove that the asymptotic convergence properties of the algorithm are preserved and numerically show that the proposed method significantly outperforms the original one.

In this paper we consider multi-objective optimization problems over a box. The problem is very relevant and several computational approaches have been proposed in the literature. They broadly fall into two main classes: evolutionary methods, which are usually very good at exploring the feasible region and retrieving good solutions even in the nonconvex case, and descent methods, which excel in efficiently approximating good quality solutions. In this paper, first we confirm, through numerical experiments, the advantages and disadvantages of these approaches. Then we propose a new method which combines the good features of both. The resulting algorithm, which we call Non-dominated Sorting Memetic Algorithm (NSMA), besides enjoying interesting theoretical properties, excels in all of the numerical tests we performed on several, widely employed, test functions., Comment: 30 pages, 8 figures

In this work the effect of an ion gel outer-layer stuck on top of ITO/PBT/Sn devices was investigated towards its effects on the electrical properties. When this external electrolyte film is in contact with any top permeable electrode it produces a self-biasing effect and changes the charge carriers injection properties. The outer-layer promoted situations where the output current increases up to two orders of magnitude and others where the output current decreases one order of magnitude in comparison to the same samples without it. Admittance spectroscopy measurements were made and the proposed equivalent circuit model indicates that the interfacial electrical properties dominate charge injection face to the bulk properties when the outer-layer is present. All the changes observed here are reversible after the ion gel is detached and replaced, indicating that ions do not diffuse into the active layer. The observed results can contribute to improve the current density in certain sandwich structures as well as notify that electrolyte external films can behave as an active layer promoting electrical changes into sandwich devices and can be extended to cases where the electrolyte film is used as substrate., Comment: 7 pages, 4 figures

We investigate the possibility of realizing a spintronic memristive device based on the dependence of the tunnel conductance on the relative angle between the magnetization of the two magnetic electrodes in in-plane magnetized tunnel junctions. For this, it is necessary to design a free layer whose magnetization can be stabilized along several or even any in-plane direction between the parallel and the antiparallel magnetic configurations. We experimentally show that this can be achieved by exploiting antiferromagnet-ferromagnet exchange interactions in a regime where the antiferromagnet is thin enough to induce enhanced coercivity and no exchange bias. The frustration of exchange interactions at the interfaces due to competing ferro- and antiferromagnetic interactions is at the origin of an isotropic dissipation mechanism yielding isotropic coercivity. From a modeling point of view, it is shown that this isotropic dissipation can be described by a dry friction term in the Landau-Lifshitz-Gilbert equation. The influence of this dry friction term on the magnetization dynamics of an in-plane magnetized layer submitted to a rotating in-plane field is investigated both analytically and numerically. The possibility to control the free layer magnetization orientation in an in-plane magnetized magnetic tunnel junction by using the spin transfer torque from an additional perpendicular polarizer is also investigated through macrospin simulation. It is shown that the memristor function can be achieved by the injection of current pulses through the stack in the presence of an in-plane static field transverse to the reference layer magnetization, the aim of which is to limit the magnetization rotation between 0{\deg} and 180{\deg}., Comment: 24 pages, 9 figures