English
Related papers

Related papers: The Effect of Network Width on Stochastic Gradient…

200 papers

The use of low-bit quantization has emerged as an indispensable technique for enabling the efficient training of large-scale models. Despite its widespread empirical success, a rigorous theoretical understanding of its impact on learning…

Machine Learning · Statistics 2026-02-17 Dechen Zhang , Junwei Su , Difan Zou

In overparametrized models, the noise in stochastic gradient descent (SGD) implicitly regularizes the optimization trajectory and determines which local minimum SGD converges to. Motivated by empirical studies that demonstrate that training…

Machine Learning · Computer Science 2021-12-07 Alex Damian , Tengyu Ma , Jason D. Lee

For infinitesimal learning rates, stochastic gradient descent (SGD) follows the path of gradient flow on the full batch loss function. However moderately large learning rates can achieve higher test accuracies, and this generalization…

Machine Learning · Computer Science 2021-01-29 Samuel L. Smith , Benoit Dherin , David G. T. Barrett , Soham De

Overparametrization is a key factor in the absence of convexity to explain global convergence of gradient descent (GD) for neural networks. Beside the well studied lazy regime, infinite width (mean field) analysis has been developed for…

Neural and Evolutionary Computing · Computer Science 2023-02-07 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and systems challenges that impede the widespread success of this…

We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. We study how regularization properties are controlled by the step-size, the number of passes and the…

Machine Learning · Computer Science 2019-03-18 Junhong Lin , Lorenzo Rosasco

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

Machine Learning · Computer Science 2021-09-16 Stephan Wojtowytsch

The mechanisms by which certain training interventions, such as increasing learning rates and applying batch normalization, improve the generalization of deep networks remains a mystery. Prior works have speculated that "flatter" solutions…

Machine Learning · Computer Science 2023-05-25 Simran Kaur , Jeremy Cohen , Zachary C. Lipton

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Several works have aimed to explain why overparameterized neural networks generalize well when trained by Stochastic Gradient Descent (SGD). The consensus explanation that has emerged credits the randomized nature of SGD for the bias of the…

Machine Learning · Computer Science 2021-02-24 Shengchao Liu , Dimitris Papailiopoulos , Dimitris Achlioptas

We present novel empirical observations regarding how stochastic gradient descent (SGD) navigates the loss landscape of over-parametrized deep neural networks (DNNs). These observations expose the qualitatively different roles of learning…

Machine Learning · Statistics 2018-05-31 Chen Xing , Devansh Arpit , Christos Tsirigotis , Yoshua Bengio

The choice of batch-size in a stochastic optimization algorithm plays a substantial role for both optimization and generalization. Increasing the batch-size used typically improves optimization but degrades generalization. To address the…

Machine Learning · Computer Science 2020-03-03 Yeming Wen , Kevin Luk , Maxime Gazeau , Guodong Zhang , Harris Chan , Jimmy Ba

Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization…

Machine Learning · Computer Science 2019-03-12 Xinyu Peng , Li Li , Fei-Yue Wang

An important question in deep learning is how higher-order optimization methods affect generalization. In this work, we analyze a stochastic Gauss-Newton (SGN) method with Levenberg-Marquardt damping and mini-batch sampling for training…

Machine Learning · Computer Science 2025-11-13 Semih Cayci

We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive regularization is imposed by stochastic process in determining…

Machine Learning · Computer Science 2020-04-15 Kensuke Nakamura , Stefano Soatto , Byung-Woo Hong

The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect for training overparameterized models. Prior theoretical work largely focuses on spherical Gaussian noise, whereas empirical studies…

Machine Learning · Computer Science 2020-06-19 Jeff Z. HaoChen , Colin Wei , Jason D. Lee , Tengyu Ma

The performance of mini-batch stochastic gradient descent (SGD) strongly depends on setting the batch size and learning rate to minimize the empirical loss in training the deep neural network. In this paper, we present theoretical analyses…

Machine Learning · Computer Science 2025-02-17 Hikaru Umeda , Hideaki Iiduka

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and -- in asynchronous implementations -- on the gradient staleness. Especially, it has been…

Machine Learning · Computer Science 2021-03-04 Sebastian U. Stich , Amirkeivan Mohtashami , Martin Jaggi

This paper explores the connection between learning trajectories of Deep Neural Networks (DNNs) and their generalization capabilities when optimized using (stochastic) gradient descent algorithms. Instead of concentrating solely on the…

Machine Learning · Computer Science 2023-11-01 Jingwen Fu , Zhizheng Zhang , Dacheng Yin , Yan Lu , Nanning Zheng