中文
相关论文

相关论文: Dimension-free convergence rates for gradient Lang…

200 篇论文

This paper proposes a novel approach to adaptive step sizes in stochastic gradient descent (SGD) by utilizing quantities that we have identified as numerically traceable -- the Lipschitz constant for gradients and a concept of the local…

最优化与控制 · 数学 2024-09-19 Frederik Köhne , Leonie Kreis , Anton Schiela , Roland Herzog

Stochastic Gradient Descent (SGD) is an out-of-equilibrium algorithm used extensively to train artificial neural networks. However very little is known on to what extent SGD is crucial for to the success of this technology and, in…

机器学习 · 计算机科学 2023-12-19 Persia Jana Kamali , Pierfrancesco Urbani

Stochastic gradient descent~(SGD) and its variants have attracted much attention in machine learning due to their efficiency and effectiveness for optimization. To handle large-scale problems, researchers have recently proposed several…

机器学习 · 统计学 2016-12-19 Shen-Yi Zhao , Gong-Duo Zhang , Wu-Jun Li

We study generalization properties of distributed algorithms in the setting of nonparametric regression over a reproducing kernel Hilbert space (RKHS). We first investigate distributed stochastic gradient methods (SGM), with mini-batches…

机器学习 · 统计学 2018-11-06 Junhong Lin , Volkan Cevher

The classical convergence analysis of SGD is carried out under the assumption that the norm of the stochastic gradient is uniformly bounded. While this might hold for some loss functions, it is violated for cases where the objective…

In this work we consider stochastic gradient descent (SGD) for solving linear inverse problems in Banach spaces. SGD and its variants have been established as one of the most successful optimisation methods in machine learning, imaging and…

机器学习 · 计算机科学 2023-02-13 Z. Kereta , B. Jin

In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a unified analysis for different data…

机器学习 · 计算机科学 2019-10-22 Chao Zhang , Jiahao Xie , Zebang Shen , Peilin Zhao , Tengfei Zhou , Hui Qian

Nonsmooth nonconvex optimization problems broadly emerge in machine learning and business decision making, whereas two core challenges impede the development of efficient solution methods with finite-time convergence guarantee: the lack of…

最优化与控制 · 数学 2022-10-18 Tianyi Lin , Zeyu Zheng , Michael I. Jordan

It is well known that adding any skew symmetric matrix to the gradient of Langevin dynamics algorithm results in a non-reversible diffusion with improved convergence rate. This paper presents a gradient algorithm to adaptively optimize the…

机器学习 · 计算机科学 2020-09-29 Vikram Krishnamurthy , George Yin

Stochastic Gradient Descent Langevin Dynamics (SGLD) algorithms, which add noise to the classic gradient descent, are known to improve the training of neural networks in some cases where the neural network is very deep. In this paper we…

计算金融 · 定量金融 2023-01-16 Pierre Bras , Gilles Pagès

We analyze the dynamics of streaming stochastic gradient descent (SGD) in the high-dimensional limit when applied to generalized linear models and multi-index models (e.g. logistic regression, phase retrieval) with general data-covariance.…

最优化与控制 · 数学 2023-08-21 Elizabeth Collins-Woodfin , Courtney Paquette , Elliot Paquette , Inbar Seroussi

Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step sizes converges weakly to the posterior distribution, the algorithm is often…

机器学习 · 统计学 2018-11-27 Nicolas Brosse , Alain Durmus , Eric Moulines

Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for…

机器学习 · 统计学 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin

We consider a class of statistical inverse problems involving the estimation of a regression operator from a Polish space to a separable Hilbert space, where the target lies in a vector-valued reproducing kernel Hilbert space induced by an…

机器学习 · 统计学 2026-04-28 Jia-Qi Yang , Lei Shi

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

机器学习 · 计算机科学 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

Recent advances in Bayesian learning with large-scale data have witnessed emergence of stochastic gradient MCMC algorithms (SG-MCMC), such as stochastic gradient Langevin dynamics (SGLD), stochastic gradient Hamiltonian MCMC (SGHMC), and…

机器学习 · 统计学 2016-10-24 Changyou Chen , Nan Ding , Lawrence Carin

We present a stochastic descent algorithm for unconstrained optimization that is particularly efficient when the objective function is slow to evaluate and gradients are not easily obtained, as in some PDE-constrained optimization and…

最优化与控制 · 数学 2024-07-08 David Kozak , Stephen Becker , Alireza Doostan , Luis Tenorio

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

机器学习 · 统计学 2022-10-07 Saad Mohamad , Hamad Alamri , Abdelhamid Bouchachia

Stochastic gradient descent (SGD) and its variants are widely used and highly effective optimization methods in machine learning, especially for neural network training. By using a single datum or a small subset of the data, selected…

数值分析 · 数学 2026-01-21 Bangti Jin , Zeljko Kereta , Yuxin Xia

In this paper, we propose a random gradient-free method for optimization in infinite dimensional Hilbert spaces, applicable to functional optimization in diverse settings. Though such problems are often solved through finite-dimensional…

最优化与控制 · 数学 2025-12-25 Caio Lins Peixoto , Daniel Csillag , Bernardo F. P. da Costa , Yuri F. Saporito