English
Related papers

Related papers: Analyzing Sharpness along GD Trajectory: Progressi…

200 papers

We demonstrate that applying an eventual decay to the learning rate (LR) in empirical risk minimization (ERM), where the mean-squared-error loss is minimized using standard gradient descent (GD) for training a two-layer neural network with…

Machine Learning · Statistics 2026-02-10 Kyle Sung , Kholood Khalil , Noah Forman , Steven Samu , Anastasis Kratsios

The dynamical stability of optimization methods at the vicinity of minima of the loss has recently attracted significant attention. For gradient descent (GD), stable convergence is possible only to minima that are sufficiently flat w.r.t.…

Machine Learning · Computer Science 2024-06-18 Rotem Mulayoff , Tomer Michaeli

We study gradient descent (GD) with a constant stepsize for $\ell_2$-regularized logistic regression with linearly separable data. Classical theory suggests small stepsizes to ensure monotonic reduction of the optimization objective,…

Machine Learning · Statistics 2025-11-04 Jingfeng Wu , Pierre Marion , Peter Bartlett

We study the trade-offs between convergence rate and robustness to gradient errors in designing a first-order algorithm. We focus on gradient descent (GD) and accelerated gradient (AG) methods for minimizing strongly convex functions when…

Optimization and Control · Mathematics 2019-11-07 Necdet Serhat Aybat , Alireza Fallah , Mert Gurbuzbalaban , Asuman Ozdaglar

Training strategies for modern deep neural networks (NNs) tend to induce a heavy-tailed (HT) empirical spectral density (ESD) in the layer weights. While previous efforts have shown that the HT phenomenon correlates with good generalization…

Machine Learning · Computer Science 2025-08-12 Vignesh Kothapalli , Tianyu Pang , Shenyang Deng , Zongmin Liu , Yaoqing Yang

Hyperparameter tuning is one of the essential steps to guarantee the convergence of machine learning models. We argue that intuition about the optimal choice of hyperparameters for stochastic gradient descent can be obtained by studying a…

Disordered Systems and Neural Networks · Physics 2025-12-12 Chanju Park , Biagio Lucini , Gert Aarts

There has been a growing effort in studying the distributed optimization problem over a network. The objective is to optimize a global function formed by a sum of local functions, using only local computation and communication. Literature…

Optimization and Control · Mathematics 2017-05-02 Guannan Qu , Na Li

In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and…

Machine Learning · Computer Science 2023-10-26 Mathieu Even , Scott Pesme , Suriya Gunasekar , Nicolas Flammarion

First-order optimization methods, such as SGD and Adam, are widely used for training large-scale deep neural networks due to their computational efficiency and robust performance. However, relying solely on gradient information, these…

Machine Learning · Computer Science 2025-07-29 Yue Hu , Zanxia Cao , Yingchao Liu

We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient…

Machine Learning · Computer Science 2022-06-07 Alexander Tyurin , Lukang Sun , Konstantin Burlachenko , Peter Richtárik

In this work, we develop new optimization algorithms that use approximate second-order information combined with the gradient regularization technique to achieve fast global convergence rates for both convex and non-convex objectives. The…

Optimization and Control · Mathematics 2025-06-17 Andrei Semenov , Martin Jaggi , Nikita Doikov

The first part of this paper studies the evolution of gradient flow for homogeneous neural networks near a class of saddle points exhibiting a sparsity structure. The choice of these saddle points is motivated from previous works on…

Machine Learning · Computer Science 2025-09-16 Akshay Kumar , Jarvis Haupt

We present a novel algorithm for training deep neural networks in supervised (classification and regression) and unsupervised (reinforcement learning) scenarios. This algorithm combines the standard stochastic gradient descent and the…

Machine Learning · Computer Science 2023-05-23 Arunselvan Ramaswamy , Shalabh Bhatnagar , Naman Saxena

Overparametrized Deep Neural Networks (DNNs) often achieve astounding performances, but may potentially result in severe generalization error. Recently, the relation between the sharpness of the loss landscape and the generalization error…

Artificial Intelligence · Computer Science 2022-05-31 Jiawei Du , Hanshu Yan , Jiashi Feng , Joey Tianyi Zhou , Liangli Zhen , Rick Siow Mong Goh , Vincent Y. F. Tan

We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a regular gradient step, and a corrective direction dictated by…

Machine Learning · Computer Science 2022-04-29 Yunfei Teng , Wenbo Gao , Francois Chalus , Anna Choromanska , Donald Goldfarb , Adrian Weller

Recent works have empirically analyzed in-context learning and shown that transformers trained on synthetic linear regression tasks can learn to implement ridge regression, which is the Bayes-optimal predictor, given sufficient capacity…

Machine Learning · Computer Science 2023-07-10 Arvind Mahankali , Tatsunori B. Hashimoto , Tengyu Ma

In this paper we study the stability and its trade-off with optimization error for stochastic gradient descent (SGD) algorithms in the pairwise learning setting. Pairwise learning refers to a learning task which involves a loss function…

Machine Learning · Computer Science 2019-04-29 Wei Shen , Zhenhuan Yang , Yiming Ying , Xiaoming Yuan

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem. Recently, \citet{zhang2019gradient} show that clipped (stochastic) Gradient Descent (GD)…

Machine Learning · Computer Science 2020-10-30 Bohang Zhang , Jikai Jin , Cong Fang , Liwei Wang

Modern deep neural networks (DNNs) have achieved state-of-the-art performances but are typically over-parameterized. The over-parameterization may result in undesirably large generalization error in the absence of other customized training…

Machine Learning · Computer Science 2023-03-03 Jiawei Du , Daquan Zhou , Jiashi Feng , Vincent Y. F. Tan , Joey Tianyi Zhou

In recent years, deep learning has been connected with optimal control as a way to define a notion of a continuous underlying learning problem. In this view, neural networks can be interpreted as a discretization of a parametric Ordinary…

Optimization and Control · Mathematics 2020-07-07 Joubine Aghili , Olga Mula