English
Related papers

Related papers: Bowl breakout, escaping the positive region when s…

200 papers

Saddle-point problems have recently gained increased attention from the machine learning community, mainly due to applications in training Generative Adversarial Networks using stochastic gradients. At the same time, in some applications…

Optimization and Control · Mathematics 2021-09-07 Abdurakhmon Sadiev , Aleksandr Beznosikov , Pavel Dvurechensky , Alexander Gasnikov

This paper proposes an asymmetric perturbation technique for solving bilinear saddle-point optimization problems, commonly arising in minimax problems, game theory, and constrained optimization. Perturbing payoffs or values is known to be…

Optimization and Control · Mathematics 2026-02-16 Kenshi Abe , Mitsuki Sakamoto , Kaito Ariu , Atsushi Iwasaki

Ising formulations are widely utilized to solve combinatorial optimization problems, and a variety of quantum or semiconductor-based hardware has recently been made available. In combinatorial optimization problems, the existence of local…

Applied Physics · Physics 2024-03-15 Yoshiki Sato , Makiko Konoshima , Hirotaka Tamura , Jun Ohkubo

We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence…

Machine Learning · Computer Science 2019-09-17 Luo Luo , Cheng Chen , Yujun Li , Guangzeng Xie , Zhihua Zhang

High-dimensional non-convex optimization problems in engineering design, control, and learning are often hindered by saddle points, flat plateaus, and strongly anisotropic curvature. This paper develops a unified, curvature-adaptive…

Optimization and Control · Mathematics 2025-09-04 Ronald Katende , Henry Kasumba

We introduce a modified model of random walk, and then develop two novel clustering algorithms based on it. In the algorithms, each data point in a dataset is considered as a particle which can move at random in space according to the…

Machine Learning · Computer Science 2008-10-31 Qiang Li , Yan He , Jing-ping Jiang

This paper presents an optimization-based receding horizon trajectory planning algorithm for dynamical systems operating in unstructured and cluttered environments. The proposed approach is a two-step procedure that uses a motion planning…

Optimization and Control · Mathematics 2019-12-12 Kristoffer Bergman , Oskar Ljungqvist , Torkel Glad , Daniel Axehill

Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first…

Machine Learning · Computer Science 2020-02-04 Matthew Staib , Sashank J. Reddi , Satyen Kale , Sanjiv Kumar , Suvrit Sra

Momentum Stochastic Gradient Descent (MSGD) algorithm has been widely applied to many nonconvex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian inference, and etc. Despite its empirical…

Machine Learning · Computer Science 2021-03-09 Tianyi Liu , Zhehui Chen , Enlu Zhou , Tuo Zhao

We consider random search processes alternating stochastically between diffusion and ballistic motion, in which the distribution function of ballistic motion directions varies from point to point in space. The specific space dependence of…

Subcellular Processes · Quantitative Biology 2016-08-29 Karsten Schwarz , Yannick Schröder , Bin Qu , Markus Hoth , Heiko Rieger

The problem of binary minimization of a quadratic functional in the configuration space is discussed. In order to increase the efficiency of the random-search algorithm it is proposed to change the energy functional by raising to a power…

Disordered Systems and Neural Networks · Physics 2011-09-02 Iakov Karandashev , Boris Kryzhanovsky

Loss functions with a large number of saddle points are one of the major obstacles for training modern machine learning models efficiently. First-order methods such as gradient descent are usually the methods of choice for training machine…

Machine Learning · Computer Science 2020-09-29 Lisa Maria Kreusser , Stanley J. Osher , Bao Wang

Computing saddle points with a prescribed Morse index on potential energy surfaces is crucial for characterizing transition states for nosie-induced rare transition events in physics and chemistry. Many numerical algorithms for this type of…

Optimization and Control · Mathematics 2025-01-28 Shuting Gu , Hao Zhang , Xiaoqun Zhang , Xiang Zhou

A strategy for finding transition paths connecting two stable basins is presented. The starting point is the Hamilton principle of stationary action; we show how it can be transformed into a minimum principle through the addition of…

Materials Science · Physics 2009-11-07 Daniele Passerone , Matteo Ceccarelli , Michele Parrinello

A classical reduced order model for dynamical problems involves spatial reduction of the problem size. However, temporal reduction accompanied by the spatial reduction can further reduce the problem size without losing accuracy much, which…

Numerical Analysis · Mathematics 2019-10-04 Youngsoo Choi , Peter Brown , Bill Arrighi , Robert Anderson

In this work, we study first-order algorithms for solving Bilevel Optimization (BO) where the objective functions are smooth but possibly nonconvex in both levels and the variables are restricted to closed convex sets. As a first step, we…

Optimization and Control · Mathematics 2024-02-13 Jeongyeol Kwon , Dohyun Kwon , Stephen Wright , Robert Nowak

Deflation techniques are typically used to shift isolated clusters of small eigenvalues in order to obtain a tighter distribution and a smaller condition number. Such changes induce a positive effect in the convergence behavior of Krylov…

Numerical Analysis · Mathematics 2024-05-15 Andrei Dumitrasc , Carola Kruse , Ulrich Ruede

Gradient descent is a popular algorithm in optimization, and its performance in convex settings is mostly well understood. In non-convex settings, it has been shown that gradient descent is able to escape saddle points asymptotically and…

Machine Learning · Computer Science 2022-08-17 Shiliang Zuo

In this paper, a sequential search method for finding the global minimum of an objective function is presented, The descent gradient search is repeated until the global minimum is obtained. The global minimum is located by a process of…

Optimization and Control · Mathematics 2024-02-06 Mohamed Tifroute , Anouar Lahmdani , Hassane Bouzahir

Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local minima, making it difficult for gradient-based optimizers to converge to the global optimum.…

Machine Learning · Computer Science 2026-02-12 Tianqi Shen , Jinji Yang , Junze He , Kunhan Gao , Ziye Ma
‹ Prev 1 8 9 10 Next ›