English
Related papers

Related papers: Does SGD really happen in tiny subspaces?

200 papers

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

Machine Learning · Computer Science 2020-07-09 Justin Goodwin , Olivia Brown , Victoria Helus

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of the feature extractor (i.e., last hidden layer) and a linear classifier (i.e., output layer) that are trained jointly with stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2022-11-28 Xin Li , Xiangrui Li , Deng Pan , Yao Qiang , Dongxiao Zhu

Despite tremendous success of deep neural network in machine learning, the underlying reason for its superior learning capability remains unclear. Here, we present a framework based on statistical physics to study dynamics of stochastic…

Machine Learning · Computer Science 2021-01-19 Yu Feng , Yuhai Tu

Spiking Neural Networks (SNNs) have attracted growing interest in both computational neuroscience and artificial intelligence, primarily due to their inherent energy efficiency and compact memory footprint. However, achieving adversarial…

Neural and Evolutionary Computing · Computer Science 2025-12-04 Luu Trong Nhan , Luu Trung Duong , Pham Ngoc Nam , Truong Cong Thang

Data imbalance is a common problem in machine learning that can have a critical effect on the performance of a model. Various solutions exist but their impact on the convergence of the learning dynamics is not understood. Here, we elucidate…

Machine Learning · Statistics 2024-02-20 Emanuele Francazi , Marco Baity-Jesi , Aurelien Lucchi

In this work, we investigate the mechanism underlying loss spikes observed during neural network training. When the training enters a region with a lower-loss-as-sharper (LLAS) structure, the training becomes unstable, and the loss…

Machine Learning · Computer Science 2024-10-08 Xiaolong Li , Zhi-Qin John Xu , Zhongwang Zhang

Despite the tremendous success of Stochastic Gradient Descent (SGD) algorithm in deep learning, little is known about how SGD finds generalizable solutions in the high-dimensional weight space. By analyzing the learning dynamics and loss…

Data Analysis, Statistics and Probability · Physics 2020-01-07 Yu Feng , Yuhai Tu

In gradient descent dynamics of neural networks, the top eigenvalue of the loss Hessian (sharpness) displays a variety of robust phenomena throughout training. This includes early time regimes where the sharpness may decrease during early…

Machine Learning · Computer Science 2025-02-17 Dayal Singh Kalra , Tianyu He , Maissam Barkeshli

During neural network training, the sharpness of the Hessian matrix of the training loss rises until training is on the edge of stability. As a result, even nonstochastic gradient descent does not accurately model the underlying dynamical…

Machine Learning · Statistics 2024-06-04 Mark Lowell , Catharine Kastner

Convolutional networks have marked their place over the last few years as the best performing model for various visual tasks. They are, however, most suited for supervised learning from large amounts of labeled data. Previous attempts have…

Machine Learning · Statistics 2016-11-23 Elad Hoffer , Itay Hubara , Nir Ailon

It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy…

Machine Learning · Computer Science 2016-07-11 Darryl D. Lin , Sachin S. Talathi

To understand how deep learning works, it is crucial to understand the training dynamics of neural networks. Several interesting hypotheses about these dynamics have been made based on empirically observed phenomena, but there exists a…

Machine Learning · Statistics 2021-11-16 Nikhil Ghosh , Song Mei , Bin Yu

Training large language models (LLMs) is often bottlenecked by extreme memory demands, with optimizer states dominating the footprint. Recent works mitigates this cost by projecting gradients into low-dimensional subspaces using…

Machine Learning · Computer Science 2025-10-03 Sahar Rajabi , Nayeema Nonta , Samanvay Vajpayee , Sirisha Rambhatla

This paper studies how neural network architecture affects the speed of training. We introduce a simple concept called gradient confusion to help formally analyze this. When gradient confusion is high, stochastic gradients produced by…

Machine Learning · Computer Science 2020-07-08 Karthik A. Sankararaman , Soham De , Zheng Xu , W. Ronny Huang , Tom Goldstein

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…

Machine Learning · Computer Science 2023-12-19 Persia Jana Kamali , Pierfrancesco Urbani

In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the…

Optimization and Control · Mathematics 2021-06-15 Mert Gurbuzbalaban , Umut Şimşekli , Lingjiong Zhu

We analyze the implicit bias of constant step stochastic subgradient descent (SGD). We consider the setting of binary classification with homogeneous neural networks - a large class of deep neural networks with ReLU-type activation…

Machine Learning · Computer Science 2025-07-18 Sholom Schechtman , Nicolas Schreuder

This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape. Local extrema with low generalization error have a large proportion of…

Neural network compression techniques have become increasingly popular as they can drastically reduce the storage and computation requirements for very large networks. Recent empirical studies have illustrated that even simple pruning…

Machine Learning · Statistics 2021-06-08 Melih Barsbey , Milad Sefidgaran , Murat A. Erdogdu , Gaël Richard , Umut Şimşekli

Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact gradient descent…

Neurons and Cognition · Quantitative Biology 2025-01-29 Christian Klos , Raoul-Martin Memmesheimer
‹ Prev 1 4 5 6 7 8 10 Next ›