English
Related papers

Related papers: Worker Disagreement Reveals Sharp Directions in Lo…

200 papers

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some…

Computation and Language · Computer Science 2018-11-05 Deren Lei , Zichen Sun , Yijun Xiao , William Yang Wang

We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions. Under a suitable choice of semimetric, we establish a contraction in…

Machine Learning · Statistics 2023-11-02 Jung Eun Huh , Patrick Rebeschini

In this paper, we examine the time it takes for stochastic gradient descent (SGD) to reach the global minimum of a general, non-convex loss function. We approach this question through the lens of randomly perturbed dynamical systems and…

Optimization and Control · Mathematics 2025-06-10 Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos

We develop a framework for analyzing the training and learning rate dynamics on a variety of high- dimensional optimization problems trained using one-pass stochastic gradient descent (SGD) with data generated from multiple anisotropic…

Machine Learning · Statistics 2025-10-17 Elizabeth Collins-Woodfin , Inbar Seroussi

Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed to generalize worse than stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2020-06-24 Jinghui Chen , Dongruo Zhou , Yiqi Tang , Ziyan Yang , Yuan Cao , Quanquan Gu

Stochastic gradient descent (SGD) is a workhorse algorithm for solving large-scale optimization problems in data science and machine learning. Understanding the convergence of SGD is hence of fundamental importance. In this work we examine…

Numerical Analysis · Mathematics 2024-12-11 Lehan Chen , Yuji Nakatsukasa

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. One thread of work has focused on…

Machine Learning · Computer Science 2020-03-24 Charles G. Frye , James Simon , Neha S. Wadia , Andrew Ligeralde , Michael R. DeWeese , Kristofer E. Bouchard

The loss and the norm of its gradient separate the healthy and the pathological regimes of neural-network training only weakly, whilst the curvature of the empirical risk differs qualitatively between them but is inaccessible explicitly at…

Machine Learning · Computer Science 2026-05-26 Maxim Bolshim , Alexander Kugaevskikh

Stein discrepancies (SDs) monitor convergence and non-convergence in approximate inference when exact integration and sampling are intractable. However, the computation of a Stein discrepancy can be prohibitive if the Stein operator - often…

Machine Learning · Statistics 2020-10-26 Jackson Gorham , Anant Raj , Lester Mackey

In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed weights, and Gaussian stochastic…

Machine Learning · Computer Science 2022-06-27 Stefano Favaro , Sandra Fortini , Stefano Peluchetti

This paper explores the suspicious alignment phenomenon in stochastic gradient descent (SGD) under ill-conditioned optimization, where the Hessian spectrum splits into dominant and bulk subspaces. This phenomenon describes the behavior of…

Machine Learning · Computer Science 2026-05-08 Shenyang Deng , Boyao Liao , Zhuoli Ouyang , Tianyu Pang , Minhak Song , Yaoqing Yang

Stochastic Gradient Descent (SGD) is commonly modeled as a Langevin process, assuming that minibatch noise acts as Brownian motion. However, this approximation relies on a continuous-time limit and a sqrt(eta) noise scaling that does not…

Stochastic Gradient Descent (SGD) is a widely deployed optimization procedure throughout data-driven and simulation-driven disciplines, which has drawn a substantial interest in understanding its global behavior across a broad class of…

Optimization and Control · Mathematics 2021-04-02 Vivak Patel , Shushu Zhang

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings…

Optimization and Control · Mathematics 2020-10-26 Jingzhao Zhang , Sai Praneeth Karimireddy , Andreas Veit , Seungyeon Kim , Sashank J Reddi , Sanjiv Kumar , Suvrit Sra

Many supervised learning tasks have intrinsic symmetries, such as translational and rotational symmetry in image classifications. These symmetries can be exploited to enhance performance. We formulate the symmetry constraints into a concise…

Quantum Physics · Physics 2024-08-14 Kaiming Bian , Shitao Zhang , Fei Meng , Wen Zhang , Oscar Dahlsten

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…

Machine Learning · Statistics 2015-12-25 Chunyuan Li , Changyou Chen , David Carlson , Lawrence Carin

Artificial neural networks can achieve impressive performances, and even outperform humans in some specific tasks. Nevertheless, unlike biological brains, the artificial neural networks suffer from tiny perturbations in sensory input, under…

Machine Learning · Computer Science 2021-03-24 Zijian Jiang , Jianwen Zhou , Haiping Huang

Recent studies have shown that heavy tails can emerge in stochastic optimization and that the heaviness of the tails have links to the generalization error. While these studies have shed light on interesting aspects of the generalization…

Machine Learning · Statistics 2023-02-14 Anant Raj , Melih Barsbey , Mert Gürbüzbalaban , Lingjiong Zhu , Umut Şimşekli

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing…

Machine Learning · Computer Science 2021-11-30 Pan Zhou , Jiashi Feng , Chao Ma , Caiming Xiong , Steven Hoi , Weinan E

For a certain scaling of the initialization of stochastic gradient descent (SGD), wide neural networks (NN) have been shown to be well approximated by reproducing kernel Hilbert space (RKHS) methods. Recent empirical work showed that, for…

Machine Learning · Statistics 2022-01-12 Behrooz Ghorbani , Song Mei , Theodor Misiakiewicz , Andrea Montanari