English
Related papers

Related papers: Error bounds for particle gradient descent, and ex…

200 papers

We derive a multiscale generalisation of the Bakry--\'Emery criterion for a measure to satisfy a Log-Sobolev inequality. Our criterion relies on the control of an associated PDE well known in renormalisation theory: the Polchinski equation.…

Probability · Mathematics 2023-10-12 Roland Bauerschmidt , Thierry Bodineau

In finite dimension, the long-time and metastable behavior of a gradient flow perturbated by a small Brownian noise is well understood. A similar situation arises when a Wasserstein gradient flow over a space of probability measure is…

Probability · Mathematics 2025-10-21 Pierre Monmarché

Sign Gradient Descent (SignGD) is a simple yet robust optimization method, widely used in machine learning for its resilience to gradient noise and compatibility with low-precision computations. While its empirical performance is well…

Optimization and Control · Mathematics 2025-08-27 Valentin Leplat , Sergio Mayorga , Roland Hildebrand , Alexander Gasnikov

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

Potential functions in highly pertinent applications, such as deep learning in over-parameterized regime, are empirically observed to admit non-isolated minima. To understand the convergence behavior of stochastic dynamics in such…

Machine Learning · Computer Science 2025-02-18 Yun Gong , Zebang Shen , Niao He

Several issues in machine learning and inverse problems require to generate discrete data, as if sampled from a model probability distribution. A common way to do so relies on the construction of a uniform probability distribution over a…

Optimization and Control · Mathematics 2021-06-16 Quentin Merigot , Filippo Santambrogio , Clément Sarrazin

Optimization and generalization are two essential aspects of statistical machine learning. In this paper, we propose a framework to connect optimization with generalization by analyzing the generalization error based on the optimization…

Machine Learning · Statistics 2022-10-13 Fusheng Liu , Haizhao Yang , Soufiane Hayou , Qianxiao Li

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

In this letter we study the proximal gradient dynamics. This recently-proposed continuous-time dynamics solves optimization problems whose cost functions are separable into a nonsmooth convex and a smooth component. First, we show that the…

Optimization and Control · Mathematics 2024-11-22 Anand Gokhale , Alexander Davydov , Francesco Bullo

This paper studies equality-constrained composite minimization problems. This class of problems, capturing regularization terms and inequality constraints, naturally arises in a wide range of engineering and machine learning applications.…

Optimization and Control · Mathematics 2026-04-13 Veronica Centorrino , Francesca Rossi , Francesco Bullo , Giovanni Russo

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

Machine Learning · Computer Science 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

We study the relationship between gradient-based optimization of parametric models (e.g., neural networks) and optimization of linear combinations of random features. Our main result shows that if a parametric model can be learned using…

Machine Learning · Computer Science 2025-05-16 Ari Karchmer , Eran Malach

We consider the problem of minimizing a convex function over a closed convex set, with Projected Gradient Descent (PGD). We propose a fully parameter-free version of AdaGrad, which is adaptive to the distance between the initialization and…

Machine Learning · Statistics 2023-06-01 Evgenii Chzhen , Christophe Giraud , Gilles Stoltz

Implicit regularization refers to the tendency of local search algorithms to converge to low-dimensional solutions, even when such structures are not explicitly enforced. Despite its ubiquity, the mechanism underlying this behavior remains…

Machine Learning · Computer Science 2025-12-10 Jianhao Ma , Geyu Liang , Salar Fattahi

We develop a novel framework to study smooth and strongly convex optimization algorithms, both deterministic and stochastic. Focusing on quadratic functions we are able to examine optimization algorithms as a recursive application of linear…

Optimization and Control · Mathematics 2015-03-25 Yossi Arjevani , Shai Shalev-Shwartz , Ohad Shamir

This paper addresses the study of derivative-free smooth optimization problems, where the gradient information on the objective function is unavailable. Two novel general derivative-free methods are proposed and developed for minimizing…

Optimization and Control · Mathematics 2023-11-29 Pham Duy Khanh , Boris S. Mordukhovich , Dat Ba Tran

We establish an improved form of the classical logarithmic Sobolev inequality for the Gaussian measure restricted to probability densities which satisfy a Poincar\'e inequality. The result implies a lower bound on the deficit in terms of…

Probability · Mathematics 2014-10-28 Max Fathi , Emanuel Indrei , Michel Ledoux

We consider minimization problems with the well-known Polya-Lojasievich condition and Lipshitz-continuous gradient. Such problem occurs in different places in machine learning and related fields. Furthermore, we assume that a gradient is…

Optimization and Control · Mathematics 2023-12-12 Sergei M. Puchinin , Fedor S. Stonyakin

In this paper we introduce two novel generalizations of the theory for gradient descent type methods in the proximal setting. First, we introduce the proportion function, which we further use to analyze all known (and many new)…

Optimization and Control · Mathematics 2017-09-12 Dominik Csiba , Peter Richtárik

We study the proximal gradient descent (PGD) method for $\ell^{0}$ sparse approximation problem as well as its accelerated optimization with randomized algorithms in this paper. We first offer theoretical analysis of PGD showing the bounded…

Optimization and Control · Mathematics 2017-09-06 Yingzhen Yang , Jiashi Feng , Nebojsa Jojic , Jianchao Yang , Thomas S. Huang
‹ Prev 1 3 4 5 6 7 10 Next ›