English
Related papers

Related papers: Conditions for linear convergence of the gradient …

200 papers

We consider a variable metric linesearch based proximal gradient method for the minimization of the sum of a smooth, possibly nonconvex function plus a convex, possibly nonsmooth term. We prove convergence of this iterative algorithm to a…

Numerical Analysis · Mathematics 2017-04-11 Silvia Bonettini , Ignace Loris , Federica Porta , Marco Prato , Simone Rebegoldi

Polyak-{\L}ojasiewicz (PL) [Polyak, 1963] condition is a weaker condition than the strong convexity but suffices to ensure a global convergence for the Gradient Descent algorithm. In this paper, we study the lower bound of algorithms using…

Optimization and Control · Mathematics 2023-08-03 Pengyun Yue , Cong Fang , Zhouchen Lin

This paper focuses on the online gradient and proximal-gradient methods with stochastic gradient errors. In particular, we examine the performance of the online gradient descent method when the cost satisfies the Polyak-\L ojasiewicz (PL)…

Optimization and Control · Mathematics 2024-07-16 Seunghyun Kim , Liam Madden , Emiliano Dall'Anese

Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range of machine learning models. However, the current theoretical understanding of its convergence rate is far from…

Machine Learning · Computer Science 2023-04-25 Yihan Zhang , Wenhao Jiang , Feng Zheng , Chiu C. Tan , Xinghua Shi , Hongchang Gao

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple…

Optimization and Control · Mathematics 2023-10-09 Quan Xiao , Songtao Lu , Tianyi Chen

We study the convergence properties of a general inertial first-order proximal splitting algorithm for solving nonconvex nonsmooth optimization problems. Using the Kurdyka--\L ojaziewicz (KL) inequality we establish new convergence rates…

Optimization and Control · Mathematics 2016-09-14 Patrick R. Johnstone , Pierre Moulin

Many practical optimization problems lack strong convexity. Fortunately, recent studies have revealed that first-order algorithms also enjoy linear convergences under various weaker regularity conditions. While the relationship among…

Optimization and Control · Mathematics 2026-02-05 Feng-Yi Liao , Lijun Ding , Yang Zheng

We consider optimization problems in which the goal is find a $k$-dimensional subspace of $\mathbb{R}^n$, $k<<n$, which minimizes a convex and smooth loss. Such problems generalize the fundamental task of principal component analysis (PCA)…

Optimization and Control · Mathematics 2022-10-27 Dan Garber , Ron Fisher

In this work, we consider smooth unconstrained optimization problems and we deal with the class of gradient methods with momentum, i.e., descent algorithms where the search direction is defined as a linear combination of the current…

Optimization and Control · Mathematics 2025-12-04 Matteo Lapucci , Giampaolo Liuzzi , Stefano Lucidi , Davide Pucci , Marco Sciandrone

We give a simple local Polyak-Lojasiewicz (PL) criterion that guarantees linear (exponential) convergence of gradient flow and gradient descent to a zero-loss solution of a nonnegative objective. We then verify this criterion for the…

Machine Learning · Computer Science 2026-02-23 Sourav Chatterjee

A fundamental class of matrix optimization problems that arise in many areas of science and engineering is that of quadratic optimization with orthogonality constraints. Such problems can be solved using line-search methods on the Stiefel…

Optimization and Control · Mathematics 2015-10-06 Huikang Liu , Weijie Wu , Anthony Man-Cho So

We propose and analyze a randomized zeroth-order approach based on approximating the exact gradient byfinite differences computed in a set of orthogonal random directions that changes with each iteration. A number ofpreviously proposed…

Optimization and Control · Mathematics 2021-11-16 David Kozak , Cesare Molinari , Lorenzo Rosasco , Luis Tenorio , Silvia Villa

The Polyak-Lojasiewicz inequality (PLI) in $\mathbb{R}^d$ is a natural condition for proving convergence of gradient descent algorithms. In the present paper, we study an analogue of PLI on the space of probability measures…

Optimization and Control · Mathematics 2023-06-06 Linshan Liu , Mateusz B. Majka , Łukasz Szpruch

It is known that when minimizing smooth Polyak-{\L}ojasiewicz (PL) functions, momentum algorithms cannot significantly improve the convergence bound of gradient descent, contrasting with the acceleration phenomenon occurring in the strongly…

Optimization and Control · Mathematics 2026-02-11 Julien Hermant

We perform the first tight convergence analysis of the gradient method with varying step sizes when applied to smooth hypoconvex (weakly convex) functions. Hypoconvex functions are smooth nonconvex functions whose curvature is bounded and…

Optimization and Control · Mathematics 2022-06-22 Teodor Rotaru , François Glineur , Panagiotis Patrinos

In this work, we develop a level-set subdifferential error bound condition aiming towards convergence rate analysis of a variable Bregman proximal gradient (VBPG) method for a broad class of nonsmooth and nonconvex optimization problems. It…

Optimization and Control · Mathematics 2020-09-01 Daoli Zhu , Sien Deng , Minghua Li , Lei Zhao

We study first order methods to compute the barycenter of a probability distribution $P$ over the space of probability measures with finite second moment. We develop a framework to derive global rates of convergence for both gradient…

Statistics Theory · Mathematics 2020-06-16 Sinho Chewi , Tyler Maunu , Philippe Rigollet , Austin J. Stromme

Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary…

Machine Learning · Computer Science 2025-05-15 Haoyuan Cai , Sulaiman A. Alghunaim , Ali H. Sayed

We investigate an inertial algorithm of gradient type in connection with the minimization of a nonconvex differentiable function. The algorithm is formulated in the spirit of Nesterov's accelerated convex gradient method. We prove some…

Functional Analysis · Mathematics 2020-02-11 Szilárd Csaba László

We characterize regions of a loss surface as corridors when the continuous curves of steepest descent -- the solutions of the gradient flow -- become straight lines. We show that corridors provide insights into gradient-based optimization,…

Machine Learning · Statistics 2024-02-15 Benoit Dherin , Mihaela Rosca