English
Related papers

Related papers: Level set methods for finding saddle points of gen…

200 papers

The saddle-point optimization problems have a lot of practical applications. This paper focuses on such non-smooth problems in decentralized case. This work contains generalization of recently proposed sliding for centralized problem.…

Optimization and Control · Mathematics 2024-01-01 Ilya Kuruzov , Alexander Rogozin , Demyan Yarmoshik , Alexander Gasnikov

We propose an inexact Uzawa algorithm with two variable relaxation parameters for solving the generalized saddle-point system. The saddle-point problems can be found in a wide class of applications, such as the augmented Lagrangian…

Numerical Analysis · Mathematics 2014-08-26 Kazufumi Ito , Hua Xiang , Jun Zou

The article is devoted to the development of numerical methods for solving saddle point problems and variational inequalities with simplified requirements for the smoothness conditions of functionals. Recently there were proposed some…

Optimization and Control · Mathematics 2023-11-22 Alexander Titov , Fedor Stonyakin , Mohammad Alkousa , Alexander Gasnikov

Recently, saddle point problems have received much attention due to their powerful modeling capability for a lot of problems from diverse domains. Applications of these problems occur in many applied areas, such as robust optimization,…

Optimization and Control · Mathematics 2022-02-15 Mohammad Alkousa , Alexander Gasnikov , Pavel Dvurechensky , Abdurakhmon Sadiev , Lama Razouk

This paper investigates the sample dependence of critical points for neural networks. We introduce a sample-independent critical lifting operator that associates a parameter of one network with a set of parameters of another, thus defining…

Machine Learning · Computer Science 2025-05-21 Leyang Zhang , Yaoyu Zhang , Tao Luo

Classical Morse theory proceeds by considering sublevel sets $f^{-1}(-\infty, a]$ of a Morse function $f: M \to R$, where $M$ is a smooth finite-dimensional manifold. In this paper, we study the topology of the level sets $f^{-1}(a)$ and…

Dynamical Systems · Mathematics 2019-10-14 Andreas Knauf , Nikolay Martynchuk

We establish that first-order methods avoid saddle points for almost all initializations. Our results apply to a wide variety of first-order methods, including gradient descent, block coordinate descent, mirror descent and variants thereof.…

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

In this paper, we introduce some adaptive methods for solving variational inequalities with relatively strongly monotone operators. Firstly, we focus on the modification of the recently proposed, in smooth case [1], adaptive numerical…

Optimization and Control · Mathematics 2022-11-01 A. A. Titov , S. S. Ablaev , M. S. Alkousa , F. S. Stonyakin , A. V. Gasnikov

We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of…

Optimization and Control · Mathematics 2020-01-13 Joan Bas-Serrano , Gergely Neu

Saddle-point problems appear in various settings including machine learning, zero-sum stochastic games, and regression problems. We consider decomposable saddle-point problems and study an extension of the alternating direction method of…

Optimization and Control · Mathematics 2022-12-29 Mustafa O. Karabag , David Fridovich-Keil , Ufuk Topcu

Level set estimation (LSE) classifies whether an unknown function's value exceeds a specified threshold for given inputs, a fundamental problem in many real-world applications. In active learning settings with limited initial data, we aim…

Machine Learning · Computer Science 2026-02-16 Giang Ngo , Dat Phan Trong , Dang Nguyen , Sunil Gupta

Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast number of high error saddle points present in the loss function.…

Numerical Analysis · Computer Science 2016-11-08 Martin Arjovsky

The paper studies a distributed gradient descent (DGD) process and considers the problem of showing that in nonconvex optimization problems, DGD typically converges to local minima rather than saddle points. The paper considers…

Optimization and Control · Mathematics 2019-10-24 Brian Swenson , Ryan Murray , H. Vincent Poor , Soummya Kar

We proposed an iterate scheme for solving convex-concave saddle-point problems associated with general convex-concave functions. We demonstrated that when our iterate scheme is applied to a special class of convex-concave functions, which…

Optimization and Control · Mathematics 2023-11-01 Hui Ouyang

Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training…

Machine Learning · Computer Science 2021-03-03 Yasaman Esfandiari , Aditya Balu , Keivan Ebrahimi , Umesh Vaidya , Nicola Elia , Soumik Sarkar

We prove error estimates for the semi-implicit numerical scheme of sphere-constrained high-index saddle dynamics, which serves as a powerful instrument in finding saddle points and constructing the solution landscapes of constrained systems…

Numerical Analysis · Mathematics 2023-07-04 Lei Zhang , Pingwen Zhang , Xiangcheng Zheng

We study a fixed step-size noisy distributed gradient descent algorithm for solving optimization problems in which the objective is a finite sum of smooth but possibly non-convex functions. Random perturbations are introduced to the…

Optimization and Control · Mathematics 2023-07-21 Lei Qin , Michael Cantoni , Ye Pu

We solve large-scale mixed-integer linear programs (MILPs) via distributed asynchronous saddle point computation. This is motivated by the MILPs being able to model problems in multi-agent autonomy, e.g., task assignment problems and…

Optimization and Control · Mathematics 2022-11-23 Luke Fina , Matthew Hale

In nearest-neighbor classification problems, a set of $d$-dimensional training points are given, each with a known classification, and are used to infer unknown classifications of other points by using the same classification as the nearest…

Data Structures and Algorithms · Computer Science 2021-10-13 David Eppstein
‹ Prev 1 3 4 5 6 7 10 Next ›