English
Related papers

Related papers: Large-Step Training Dynamics of a Two-Factor Linea…

200 papers

The recipe behind the success of deep learning has been the combination of neural networks and gradient-based optimization. Understanding the behavior of gradient descent however, and particularly its instability, has lagged behind its…

Machine Learning · Statistics 2023-09-15 Mihaela Rosca , Yan Wu , Chongli Qin , Benoit Dherin

Conventional wisdom dictates that learning rate should be in the stable regime so that gradient-based algorithms don't blow up. This letter introduces a simple scenario where an unstably large learning rate scheme leads to a super fast…

Machine Learning · Computer Science 2021-09-08 Samet Oymak

Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has found significant empirical success. However, a principled understanding of why it works is lacking. This…

Machine Learning · Computer Science 2026-05-08 Joe Suk , Yaqi Duan

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Machine Learning · Statistics 2026-04-21 Hossein Taheri , Avishek Ghosh , Arya Mazumdar

In this paper, we study the dynamics of gradient descent in learning neural networks for classification problems. Unlike in existing works, we consider the linearly non-separable case where the training data of different classes lie in…

Machine Learning · Computer Science 2020-12-11 Ziang Long , Penghang Yin , Jack Xin

It has been shown that gradient descent can yield the zero training loss in the over-parametrized regime (the width of the neural networks is much larger than the number of data points). In this work, combining the ideas of some existing…

Optimization and Control · Mathematics 2019-11-05 Lei Li

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…

Machine Learning · Statistics 2026-05-19 Naman Agarwal , Siddhartha R. Dalal , Vishal Misra

We consider the approximation of functions by 2-layer neural networks with a small number of hidden weights based on the squared loss and small datasets. Due to the highly non-convex energy landscape, gradient-based training often suffers…

Machine Learning · Computer Science 2025-08-14 Johannes Hertrich , Sebastian Neumayer

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in…

Machine Learning · Statistics 2024-11-01 Cheng Gao , Yuan Cao , Zihao Li , Yihan He , Mengdi Wang , Han Liu , Jason Matthew Klusowski , Jianqing Fan

Training deep neural networks typically relies on backpropagating high dimensional error signals a computationally intensive process with little evidence supporting its implementation in the brain. However, since most tasks involve…

Machine Learning · Computer Science 2026-01-15 Maher Hanut , Jonathan Kadmon

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just…

Machine Learning · Computer Science 2022-11-24 Jeremy M. Cohen , Simran Kaur , Yuanzhi Li , J. Zico Kolter , Ameet Talwalkar

Deep unfolding is a promising deep-learning technique, whose network architecture is based on expanding the recursive structure of existing iterative algorithms. Although convergence acceleration is a remarkable advantage of deep unfolding,…

Machine Learning · Computer Science 2020-10-27 Satoshi Takabe , Tadashi Wadayama

A major challenge in training large-scale machine learning models is configuring the training process to maximize model performance, i.e., finding the best training setup from a vast design space. In this work, we unlock a gradient-based…

Machine Learning · Statistics 2025-03-19 Logan Engstrom , Andrew Ilyas , Benjamin Chen , Axel Feldmann , William Moses , Aleksander Madry

Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as training of neural networks. The key insight, already…

Probability · Mathematics 2020-12-15 Kaitong Hu , Zhenjie Ren , David Siska , Lukasz Szpruch

We study the implicit regularization imposed by gradient descent for learning multi-layer homogeneous functions including feed-forward fully connected and convolutional deep neural networks with linear, ReLU or Leaky ReLU activation. We…

Machine Learning · Computer Science 2018-11-01 Simon S. Du , Wei Hu , Jason D. Lee

The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its success is still missing. This article presents, for…

Machine Learning · Statistics 2026-04-15 Etienne Boursier , Loucas Pillaud-Vivien , Nicolas Flammarion

This paper revisits the special type of a neural network known under two names. In the statistics and machine learning community it is known as a multi-class logistic regression neural network. In the neural network community, it is simply…

Machine Learning · Statistics 2021-01-29 Marek Rychlik

We reconsider the stochastic (sub)gradient approach to the unconstrained primal L1-SVM optimization. We observe that if the learning rate is inversely proportional to the number of steps, i.e., the number of times any training pattern is…

Machine Learning · Computer Science 2014-01-28 Constantinos Panagiotakopoulos , Petroula Tsampouka