English
Related papers

Related papers: Acceleration for Polyak-{\L}ojasiewicz Functions w…

200 papers

In this paper, we provide near-optimal accelerated first-order methods for minimizing a broad class of smooth nonconvex functions that are strictly unimodal on all lines through a minimizer. This function class, which we call the class of…

Optimization and Control · Mathematics 2023-02-27 Oliver Hinder , Aaron Sidford , Nimit S. Sohoni

Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well…

Machine Learning · Computer Science 2024-07-18 Kushal Chakrabarti , Mayank Baranwal

Nonconvex-nonconcave minimax optimization has gained widespread interest over the last decade. However, most existing works focus on variants of gradient descent-ascent (GDA) algorithms, which are only applicable to smooth nonconvex-concave…

Optimization and Control · Mathematics 2025-01-17 Jiajin Li , Linglingzhi Zhu , Anthony Man-Cho So

In this paper we study a second order dynamical system with variable coefficients in connection to the minimization problem of a smooth nonconvex function. The convergence of the trajectories generated by the dynamical system to a critical…

Optimization and Control · Mathematics 2025-10-21 Szilárd Csaba László

In this paper we present an abstract convergence analysis of inexact descent methods in Riemannian context for functions satisfying Kurdyka-Lojasiewicz inequality. In particular, without any restrictive assumption about the sign of the…

Numerical Analysis · Mathematics 2011-03-25 G. C. Bento , J. X. da Cruz Neto , P. R. Oliveira

In 1964, Polyak showed that the Heavy-ball method, the simplest momentum technique, accelerates convergence of strongly-convex problems in the vicinity of the solution. While Nesterov later developed a globally accelerated version, Polyak's…

Optimization and Control · Mathematics 2023-01-18 Antonio Orvieto

In this note, we establish a new exact worst-case linear convergence rate of the proximal gradient method in terms of the proximal gradient norm, which complements the recent results in [1] and implies a refined descent lemma.descent lemma.…

Optimization and Control · Mathematics 2019-03-13 Xiaoya Zhang , Hui Zhang

The success of deep learning over the past decade mainly relies on gradient-based optimisation and backpropagation. This paper focuses on analysing the performance of first-order gradient-based optimisation algorithms, gradient descent and…

Optimization and Control · Mathematics 2022-12-08 Behnam Mafakheri , Iman Shames , Jonathan H. Manton

We develop a new Riemannian descent algorithm that relies on momentum to improve over existing first-order methods for geodesically convex optimization. In contrast, accelerated convergence rates proved in prior work have only been shown to…

Optimization and Control · Mathematics 2021-02-16 Foivos Alimisis , Antonio Orvieto , Gary Bécigneul , Aurelien Lucchi

In this paper, we consider a class of nonconvex-nonconcave minimax problems, i.e., NC-PL minimax problems, whose objective functions satisfy the Polyak-\L ojasiewicz (PL) condition with respect to the inner variable. We propose a…

Optimization and Control · Mathematics 2023-05-30 Zi Xu , Zi-Qi Wang , Jun-Lin Wang , Yu-Hong Dai

We present theoretical results on the convergence of \emph{non-convex} accelerated gradient descent in matrix factorization models with $\ell_2$-norm loss. The purpose of this work is to study the effects of acceleration in non-convex…

Machine Learning · Computer Science 2019-09-24 Tayo Ajayi , David Mildebrath , Anastasios Kyrillidis , Shashanka Ubaru , Georgios Kollias , Kristofer Bouchard

Stochastic nonconvex-concave min-max saddle point problems appear in many machine learning and control problems including distributionally robust optimization, generative adversarial networks, and adversarial learning. In this paper, we…

Optimization and Control · Mathematics 2023-09-12 Morteza Boroun , Zeinab Alizadeh , Afrooz Jalilzadeh

In this work, we propose an adaptive variation on the classical Heavy-ball method for convex quadratic minimization. The adaptivity crucially relies on so-called "Polyak step-sizes", which consists in using the knowledge of the optimal…

Optimization and Control · Mathematics 2022-10-13 Baptiste Goujaud , Adrien Taylor , Aymeric Dieuleveut

In this work, we establish that Nesterov's accelerated gradient method, applied to $C^2$ functions satisfying the Polyak--{\L}ojasiewicz inequality around local minimizers, achieves the optimal local linear convergence rate…

Optimization and Control · Mathematics 2026-03-24 Zixu Feng , Hao Yuan

The stochastic proximal gradient method is a powerful generalization of the widely used stochastic gradient descent (SGD) method and has found numerous applications in Machine Learning. However, it is notoriously known that this method…

Optimization and Control · Mathematics 2024-12-10 Yuan Gao , Anton Rodomanov , Sebastian U. Stich

We consider a composite optimization problem where the sum of a continuously differentiable and a merely lower semicontinuous function has to be minimized. The proximal gradient algorithm is the classical method for solving such a problem…

Optimization and Control · Mathematics 2023-05-01 Xiaoxi Jia , Christian Kanzow , Patrick Mehlitz

There are much recent interests in solving noncovnex min-max optimization problems due to its broad applications in many areas including machine learning, networked resource allocations, and distributed optimization. Perhaps, the most…

Optimization and Control · Mathematics 2021-12-20 Thinh T. Doan

The asymptotic analysis of a generic stochastic optimization algorithm mainly relies on the establishment of a specific descent condition. While the convexity assumption allows for technical shortcuts and generally leads to strict…

Optimization and Control · Mathematics 2024-04-09 Jean-Baptiste Fest

Most prior work on the convergence of gradient descent (GD) for overparameterized neural networks relies on strong assumptions on the step size (infinitesimal), the hidden-layer width (infinite), or the initialization (large, spectral,…

Machine Learning · Computer Science 2025-05-20 Ziqing Xu , Hancheng Min , Salma Tarmoun , Enrique Mallada , Rene Vidal

This paper is devoted to the class of paraconvex functions and presents some of its fundamental properties, characterization, and examples that can be used for their recognition and optimization. Next, the convergence analysis of the…

Optimization and Control · Mathematics 2026-03-06 Morteza Rahimi , Susan Ghaderi , Yves Moreau , Masoud Ahookhosh