English
Related papers

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

200 papers

In this paper, we first present an explanation regarding the common occurrence of spikes in the training loss when neural networks are trained with stochastic gradient descent (SGD). We provide evidence that the spikes in the training loss…

Machine Learning · Computer Science 2024-06-07 Libin Zhu , Chaoyue Liu , Adityanarayanan Radhakrishnan , Mikhail Belkin

Neural networks trained to solve modular arithmetic tasks exhibit grokking, a phenomenon where the test accuracy starts improving long after the model achieves 100% training accuracy in the training process. It is often taken as an example…

Gradient Descent (GD) is a ubiquitous algorithm for finding the optimal solution to an optimization problem. For reduced computational complexity, the optimal solution $\mathrm{x^*}$ of the optimization problem must be attained in a minimum…

Optimization and Control · Mathematics 2023-06-01 Revati Gunjal , Sushama Wagh , Syed Shadab Nayyer , Alex Stankovic , Navdeep M. Singh

Deep learning sometimes appears to work in unexpected ways. In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network consisting of a sequence of…

Machine Learning · Computer Science 2024-11-04 Alan Jeffares , Alicia Curth , Mihaela van der Schaar

Convergence detection of iterative stochastic optimization methods is of great practical interest. This paper considers stochastic gradient descent (SGD) with a constant learning rate and momentum. We show that there exists a transient…

Machine Learning · Computer Science 2020-08-28 Jerry Chee , Ping Li

In this paper, we propose a novel normalization method called gradient normalization (GN) to tackle the training instability of Generative Adversarial Networks (GANs) caused by the sharp gradient space. Unlike existing work such as gradient…

Machine Learning · Computer Science 2021-10-12 Yi-Lun Wu , Hong-Han Shuai , Zhi-Rui Tam , Hong-Yu Chiu

Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in runtime as it waits for the slowest workers (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness…

Machine Learning · Statistics 2020-03-25 Sanghamitra Dutta , Jianyu Wang , Gauri Joshi

Stochastic Gradient Descent (SGD) is widely used in machine learning problems to efficiently perform empirical risk minimization, yet, in practice, SGD is known to stall before reaching the actual minimizer of the empirical risk. SGD…

Machine Learning · Statistics 2017-02-09 Vivak Patel

We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation…

Computation and Language · Computer Science 2025-02-07 Ang Lv , Ruobing Xie , Xingwu Sun , Zhanhui Kang , Rui Yan

The performance of gradient-based optimization methods, such as standard gradient descent (GD), greatly depends on the choice of learning rate. However, it can require a non-trivial amount of user tuning effort to select an appropriate…

Machine Learning · Computer Science 2025-10-14 Nikola Surjanovic , Alexandre Bouchard-Côté , Trevor Campbell

Grokking describes a delayed generalization phenomenon in which a neural network achieves perfect training accuracy long before validation accuracy improves, followed by an abrupt transition to strong generalization. Existing detection…

Machine Learning · Computer Science 2026-04-24 Shreel Golwala

We derive a simple and model-independent formula for the change in the generalization gap due to a gradient descent update. We then compare the change in the test error for stochastic gradient descent to the change in test error from an…

Machine Learning · Computer Science 2021-04-13 Daniel A. Roberts

Machine learning has made tremendous progress in recent years, with models matching or even surpassing humans on a series of specialized tasks. One key element behind the progress of machine learning in recent years has been the ability to…

Machine Learning · Computer Science 2020-06-30 Giorgi Nadiradze , Ilia Markov , Bapi Chatterjee , Vyacheslav Kungurtsev , Dan Alistarh

The grokking phenomenon as reported by Power et al. ( arXiv:2201.02177 ) refers to a regime where a long period of overfitting is followed by a seemingly sudden transition to perfect generalization. In this paper, we attempt to reveal the…

Machine Learning · Computer Science 2022-06-14 Vimal Thilak , Etai Littwin , Shuangfei Zhai , Omid Saremi , Roni Paiss , Joshua Susskind

Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training…

Machine Learning · Computer Science 2026-04-06 Yongzhong Xu

A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data. In this work, we show…

Machine Learning · Computer Science 2021-12-14 Yatin Dandi , Luis Barba , Martin Jaggi

Gradient descent algorithm is the most utilized method when optimizing machine learning issues. However, there exists many local minimums and saddle points in the loss function, especially for high dimensional non-convex optimization…

Machine Learning · Computer Science 2021-07-19 Zhicheng Cai

A key challenge for the machine learning community is to understand and accelerate the training dynamics of deep networks that lead to delayed generalisation and emergent robustness to input perturbations, also known as grokking. Prior work…

Machine Learning · Computer Science 2025-08-01 Thomas Walker , Ahmed Imtiaz Humayun , Randall Balestriero , Richard Baraniuk

Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data. We try to understand this seemingly strange phenomenon through the…

Machine Learning · Computer Science 2024-02-05 Zhiquan Tan , Weiran Huang

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee