English
Related papers

Related papers: Egalitarian Gradient Descent: A Simple Approach to…

200 papers

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Machine Learning · Computer Science 2024-08-21 Huixiu Jiang , Ling Yang , Yu Bao , Rutong Si , Sikun Yang

The purpose of this paper is to improve upon existing variants of gradient descent by solving two problems: (1) removing (or reducing) the plateau that occurs while minimizing the cost function, (2) continually adjusting the learning rate…

Machine Learning · Computer Science 2021-08-04 Michael F. Zimmer

In overparameterized logistic regression, gradient descent (GD) iterates diverge in norm while converging in direction to the maximum $\ell_2$-margin solution -- a phenomenon known as the implicit bias of GD. This work investigates…

Machine Learning · Computer Science 2025-07-01 Jingfeng Wu , Peter Bartlett , Matus Telgarsky , Bin Yu

Grokking is a puzzling phenomenon in neural networks where full generalization occurs only after a substantial delay following the complete memorization of the training data. Previous research has linked this delayed generalization to…

Machine Learning · Computer Science 2026-01-12 Tiberiu Musat

Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness that can…

Machine Learning · Statistics 2018-05-11 Sanghamitra Dutta , Gauri Joshi , Soumyadip Ghosh , Parijat Dube , Priya Nagpurkar

Understanding neural network's (NN) generalizability remains a central question in deep learning research. The special phenomenon of grokking, where NNs abruptly generalize long after the training performance reaches a near-perfect level,…

Machine Learning · Computer Science 2026-01-06 Xiaotian Zhang , Yue Shang , Entao Yang , Ge Zhang

Machine learning models are often learned by minimising a loss function on the training data using a gradient descent algorithm. These models often suffer from overfitting, leading to a decline in predictive performance on unseen data. A…

When applied to training deep neural networks, stochastic gradient descent (SGD) often incurs steady progression phases, interrupted by catastrophic episodes in which loss and gradient norm explode. A possible mitigation of such events is…

Machine Learning · Statistics 2017-09-06 Alice Schoenauer-Sebag , Marc Schoenauer , Michèle Sebag

It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal…

Machine Learning · Computer Science 2023-01-30 Jikai Jin , Zhiyuan Li , Kaifeng Lyu , Simon S. Du , Jason D. Lee

In this paper, we study the implicit regularization of stochastic gradient descent (SGD) through the lens of {\em dynamical stability} (Wu et al., 2018). We start by revising existing stability analyses of SGD, showing how the Frobenius…

Machine Learning · Statistics 2023-06-02 Lei Wu , Weijie J. Su

One of the most surprising puzzles in neural network generalisation is grokking: a network with perfect training accuracy but poor generalisation will, upon further training, transition to perfect generalisation. We propose that grokking…

Machine Learning · Computer Science 2023-09-06 Vikrant Varma , Rohin Shah , Zachary Kenton , János Kramár , Ramana Kumar

We study stochastic gradient descent (SGD) for composite optimization problems with $N$ sequential operators subject to perturbations in both the forward and backward passes. Unlike classical analyses that treat gradient noise as additive…

Optimization and Control · Mathematics 2026-02-25 Boao Kong , Hengrui Zhang , Kun Yuan

Based on SGD, previous works have proposed many algorithms that have improved convergence speed and generalization in stochastic optimization, such as SGDm, AdaGrad, Adam, etc. However, their convergence analysis under non-convex conditions…

Machine Learning · Computer Science 2024-02-05 Yichuan Deng , Zhao Song , Chiwun Yang

While the phenomenon of grokking, i.e., delayed generalization, has been studied extensively, it remains an open problem whether there is a mathematical framework that characterizes what kind of features will emerge, how and in which…

Machine Learning · Computer Science 2025-12-03 Yuandong Tian

Stochastic gradient descent is an optimisation method that combines classical gradient descent with random subsampling within the target functional. In this work, we introduce the stochastic gradient process as a continuous-time…

Probability · Mathematics 2021-05-11 Jonas Latz

Delayed generalization, termed grokking, in a machine learning calculation occurs when the increase in test accuracy is delayed relative to the training accuracy. This paper examines grokking in the context of a dense neural network trained…

Disordered Systems and Neural Networks · Physics 2026-02-06 Karolina Hutchison , David Yevick

It has been observed by Belkin et al.\ that over-parametrized neural networks exhibit a `double descent' phenomenon. That is, as the model complexity (as reflected in the number of features) increases, the test error initially decreases,…

Optimization and Control · Mathematics 2025-09-16 Vivek Shripad Borkar

Recent studies have uncovered intriguing phenomena in deep learning, such as grokking, double descent, and emergent abilities in large language models, which challenge human intuition and are crucial for a deeper understanding of neural…

Machine Learning · Computer Science 2024-02-27 Yufei Huang , Shengding Hu , Xu Han , Zhiyuan Liu , Maosong Sun

Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach to understanding emergence is to find continuous…

Machine Learning · Computer Science 2023-10-23 Neel Nanda , Lawrence Chan , Tom Lieberum , Jess Smith , Jacob Steinhardt

We investigate grokking in transformers through the lens of inductive bias: dispositions arising from architecture or optimization that let the network prefer one solution over another. We first show that architectural choices such as the…

Machine Learning · Computer Science 2026-02-09 Jaisidh Singh , Diganta Misra , Antonio Orvieto