中文
相关论文

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

200 篇论文

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

机器学习 · 计算机科学 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

We provide the first theoretical analysis on the convergence rate of the asynchronous stochastic variance reduced gradient (SVRG) descent algorithm on non-convex optimization. Recent studies have shown that the asynchronous stochastic…

机器学习 · 计算机科学 2016-12-21 Zhouyuan Huo , Heng Huang

In this work, we propose a novel adaptive stochastic gradient-free (ASGF) approach for solving high-dimensional nonconvex optimization problems based on function evaluations. We employ a directional Gaussian smoothing of the target function…

最优化与控制 · 数学 2022-01-19 Anton Dereventsov , Clayton G. Webster , Joseph D. Daws

Stochastic-gradient sampling methods are often used to perform Bayesian inference on neural networks. It has been observed that the methods in which notions of differential geometry are included tend to have better performances, with the…

机器学习 · 计算机科学 2024-04-02 Hanlin Yu , Marcelo Hartmann , Bernardo Williams , Arto Klami

Langevin dynamics has found a large number of applications in sampling, optimization and estimation. Preconditioning the gradient in the dynamics with the covariance - an idea that originated in literature related to solving estimation and…

概率论 · 数学 2025-04-28 Axel Ringh , Akash Sharma

Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. While the empirical success of SGD is often attributed to its computational efficiency…

机器学习 · 统计学 2022-06-16 Courtney Paquette , Elliot Paquette , Ben Adlam , Jeffrey Pennington

Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving two stages of sampling: Firstly, we regress from…

机器学习 · 统计学 2021-03-08 Nicole Mücke

In this paper, we show that simple {Stochastic} subGradient Decent methods with multiple Restarting, named {\bf RSGD}, can achieve a \textit{linear convergence rate} for a class of non-smooth and non-strongly convex optimization problems…

机器学习 · 计算机科学 2016-04-01 Tianbao Yang , Qihang Lin

In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order $2$. Using…

统计计算 · 统计学 2018-03-30 Alain Durmus , Szymon Majewski , Błażej Miasojedow

We analyze in a closed form the learning dynamics of stochastic gradient descent (SGD) for a single-layer neural network classifying a high-dimensional Gaussian mixture where each cluster is assigned one of two labels. This problem provides…

机器学习 · 计算机科学 2022-03-28 Francesca Mignacco , Florent Krzakala , Pierfrancesco Urbani , Lenka Zdeborová

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several…

机器学习 · 统计学 2017-10-02 Qi Meng , Wei Chen , Yue Wang , Zhi-Ming Ma , Tie-Yan Liu

Stochastic gradient descent (SGD) on a low-rank factorization is commonly employed to speed up matrix problems including matrix completion, subspace tracking, and SDP relaxation. In this paper, we exhibit a step size scheme for SGD on a…

机器学习 · 计算机科学 2015-02-11 Christopher De Sa , Kunle Olukotun , Christopher Ré

Stochastic gradient descent (SGD) gives an optimal convergence rate when minimizing convex stochastic objectives $f(x)$. However, in terms of making the gradients small, the original SGD does not give an optimal rate, even when $f(x)$ is…

机器学习 · 计算机科学 2021-07-30 Zeyuan Allen-Zhu

Local SGD is a promising approach to overcome the communication overhead in distributed learning by reducing the synchronization frequency among worker nodes. Despite the recent theoretical advances of local SGD in empirical risk…

机器学习 · 计算机科学 2021-03-01 Yuyang Deng , Mehrdad Mahdavi

We study stochastic gradient descent (SGD) with gradient clipping on convex functions under a generalized smoothness assumption called $(L_0,L_1)$-smoothness. Using gradient clipping, we establish a high probability convergence rate that…

最优化与控制 · 数学 2025-06-04 Ofir Gaash , Kfir Yehuda Levy , Yair Carmon

Stochastic Gradient Descent (SGD) plays a central role in modern machine learning. While there is extensive work on providing error upper bound for SGD, not much is known about SGD error lower bound. In this paper, we study the convergence…

最优化与控制 · 数学 2019-10-21 Zhiyan Ding , Yiding Chen , Qin Li , Xiaojin Zhu

The simulation of high-dimensional problems with manageable computational resource represents a long-standing challenge. In a series of our recent work [25, 17, 18, 24], a class of sparse grid DG methods has been formulated for solving…

数值分析 · 数学 2019-06-27 Wei Guo

Stochastic gradients have been widely integrated into Langevin-based methods to improve their scalability and efficiency in solving large-scale sampling problems. However, the proximal sampler, which exhibits much faster convergence than…

机器学习 · 统计学 2024-05-28 Xunpeng Huang , Difan Zou , Yi-An Ma , Hanze Dong , Tong Zhang

Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning…

机器学习 · 统计学 2010-07-02 Gui-Bo Ye , Xiaohui Xie

Robust discretization methods for (nearly-incompressible) linear elasticity are free of volume-locking and gradient-robust. While volume-locking is a well-known problem that can be dealt with in many different discretization approaches, the…

数值分析 · 数学 2020-01-24 Guosheng Fu , Christoph Lehrenfeld , Alexander Linke , Timo Streckenbach