English
Related papers

Related papers: First-order methods almost always avoid saddle poi…

200 papers

A central challenge to many fields of science and engineering involves minimizing non-convex error functions over continuous, high dimensional spaces. Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such…

Machine Learning · Computer Science 2014-05-29 Razvan Pascanu , Yann N. Dauphin , Surya Ganguli , Yoshua Bengio

The standard assumption for proving linear convergence of first order methods for smooth convex optimization is the strong convexity of the objective function, an assumption which does not hold for many practical applications. In this…

Optimization and Control · Mathematics 2016-08-10 I. Necoara , Yu. Nesterov , F. Glineur

We consider the problem of minimizing a differentiable function with locally Lipschitz continuous gradient on a stratified set and present a first-order algorithm designed to find a stationary point of that problem. Our assumptions on the…

Optimization and Control · Mathematics 2023-03-29 Guillaume Olikier , Kyle A. Gallivan , P. -A. Absil

Shuffling-type gradient methods are favored in practice for their simplicity and rapid empirical performance. Despite extensive development of convergence guarantees under various assumptions in recent years, most require the Lipschitz…

Machine Learning · Computer Science 2025-07-15 Qi He , Peiran Yu , Ziyi Chen , Heng Huang

In the paper, we generalize the approach Gasnikov et. al, 2017, which allows to solve (stochastic) convex optimization problems with an inexact gradient-free oracle, to the convex-concave saddle-point problem. The proposed approach works,…

Optimization and Control · Mathematics 2022-09-13 Aleksandr Beznosikov , Abdurakhmon Sadiev , Alexander Gasnikov

One of the most attractive recent approaches to processing well-structured large-scale convex optimization problems is based on smooth convex-concave saddle point reformu-lation of the problem of interest and solving the resulting problem…

Data Structures and Algorithms · Computer Science 2014-05-22 Aharon Ben-Tal , Arkadi Nemirovski

We focus on nonconvex and nonsmooth minimization problems with a composite objective, where the differentiable part of the objective is freed from the usual and restrictive global Lipschitz gradient continuity assumption. This longstanding…

Optimization and Control · Mathematics 2017-06-21 Jérôme Bolte , Shoham Sabach , Marc Teboulle , Yakov Vaisbourd

Gradient descent is the primary workhorse for optimizing large-scale problems in machine learning. However, its performance is highly sensitive to the choice of the learning rate. A key limitation of gradient descent is its lack of natural…

Optimization and Control · Mathematics 2025-07-15 Oscar Smee , Fred Roosta , Stephen J. Wright

On solving a convex-concave bilinear saddle-point problem (SPP), there have been many works studying the complexity results of first-order methods. These results are all about upper complexity bounds, which can determine at most how many…

Optimization and Control · Mathematics 2018-08-10 Yuyuan Ouyang , Yangyang Xu

In this paper we consider discrete gradient methods for approximating the solution and preserving a first integral (also called a constant of motion) of autonomous ordinary differential equations. We prove under mild conditions for a large…

Numerical Analysis · Mathematics 2013-01-22 Richard A. Norton , G. R. W. Quispel

It is known that step size adaptive evolution strategies (ES) do not converge (prematurely) to regular points of continuously differentiable objective functions. Among critical points, convergence to minima is desired, and convergence to…

Neural and Evolutionary Computing · Computer Science 2022-06-22 Tobias Glasmachers

This paper focuses on systems of nonlinear second-order stochastic differential equations with multi-scales. The motivation for our study stems from mathematical physics and statistical mechanics, for examples, Langevin dynamics and…

Probability · Mathematics 2024-04-08 Nhu N. Nguyen , George Yin

Saddle points constitute a crucial challenge for first-order gradient descent algorithms. In notions of classical machine learning, they are avoided for example by means of stochastic gradient descent methods. In this work, we provide…

Quantum Physics · Physics 2025-05-26 Junyu Liu , Frederik Wilde , Antonio Anna Mele , Xin Jin , Liang Jiang , Jens Eisert

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

When the nonconvex problem is complicated by stochasticity, the sample complexity of stochastic first-order methods may depend linearly on the problem dimension, which is undesirable for large-scale problems. To alleviate this linear…

Optimization and Control · Mathematics 2025-09-30 Yue Xie , Jiawen Bi , Hongcheng Liu

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

Gradient-related first-order methods have become the workhorse of large-scale numerical optimization problems. Many of these problems involve nonconvex objective functions with multiple saddle points, which necessitates an understanding of…

Optimization and Control · Mathematics 2022-03-10 Rishabh Dixit , Mert Gurbuzbalaban , Waheed U. Bajwa

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a…

Machine Learning · Statistics 2019-02-28 Xiaoyu Li , Francesco Orabona

Gradient-based optimization of neural differential equations and other parameterized dynamical systems fundamentally relies on the ability to differentiate numerical solutions with respect to model parameters. In stiff systems, it has been…

Machine Learning · Computer Science 2025-08-05 Colby Fronk , Linda Petzold

We consider the problem of finding a saddle point for the convex-concave objective $\min_x \max_y f(x) + \langle Ax, y\rangle - g^*(y)$, where $f$ is a convex function with locally Lipschitz gradient and $g$ is convex and possibly…

Optimization and Control · Mathematics 2021-10-29 Maria-Luiza Vladarean , Yura Malitsky , Volkan Cevher