English
Related papers

Related papers: Extreme Memorization via Scale of Initialization

200 papers

Machine learning models often rely on simple spurious features -- patterns in training data that correlate with targets but are not causally related to them, like image backgrounds in foreground classification. This reliance typically leads…

Machine Learning · Computer Science 2025-06-06 Chenyu You , Haocheng Dai , Yifei Min , Jasjeet S. Sekhon , Sarang Joshi , James S. Duncan

In this paper we study the problem of learning Rectified Linear Units (ReLUs) which are functions of the form $max(0,<w,x>)$ with $w$ denoting the weight vector. We study this problem in the high-dimensional regime where the number of…

Machine Learning · Computer Science 2017-08-03 Mahdi Soltanolkotabi

Deep neural networks, which employ batch normalization and ReLU-like activation functions, suffer from instability in the early stages of training due to the high gradient induced by temporal gradient explosion. In this study, we analyze…

Machine Learning · Computer Science 2023-05-23 Inyoung Paik , Jaesik Choi

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

In this paper we investigate the generalization error of gradient descent (GD) applied to an $\ell_2$-regularized OLS objective function in the linear model. Based on our analysis we develop new methodology for computationally tractable and…

Statistics Theory · Mathematics 2026-01-27 Thomas Stark , Lukas Steinberger

We present a new approach for input optimization of ReLU networks that explicitly takes into account the effect of changes in activation patterns. We analyze local optimization steps in both the input space and the space of activation…

Machine Learning · Computer Science 2024-06-04 Hongzhan Yu , Sicun Gao

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such…

Machine Learning · Computer Science 2021-07-23 Deep Patel , P. S. Sastry

Spectral optimizers such as Muon have recently shown strong empirical performance in large-scale language model training, but the source and extent of their advantage remain poorly understood. We study this question through the linear…

Machine Learning · Computer Science 2026-04-29 Juno Kim , Eshaan Nichani , Denny Wu , Alberto Bietti , Jason D. Lee

In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capacity of a neural network architecture: the largest number of…

Machine Learning · Statistics 2024-12-09 Sjoerd Dirksen , Patrick Finke , Martin Genzel

In many numerical simulations stochastic gradient descent (SGD) type optimization methods perform very effectively in the training of deep neural networks (DNNs) but till this day it remains an open problem of research to provide a…

Machine Learning · Computer Science 2023-06-26 Martin Hutzenthaler , Arnulf Jentzen , Katharina Pohl , Adrian Riekert , Luca Scarpa

In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the iterates go further into the past. For example, gradient…

Machine Learning · Computer Science 2026-01-14 Matias D. Cattaneo , Boris Shigida

The ability to learn different tasks sequentially is essential to the development of artificial intelligence. In general, neural networks lack this capability, the major obstacle being catastrophic forgetting. It occurs when the…

Machine Learning · Computer Science 2021-10-22 Kaustubh Olpadkar , Ekta Gavas

Recent years have seen considerable progress in the continual training of deep neural networks, predominantly thanks to approaches that add replay or regularization terms to the loss function to approximate the joint loss over all tasks so…

Machine Learning · Computer Science 2024-11-01 Timm Hess , Tinne Tuytelaars , Gido M. van de Ven

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse…

Machine Learning · Computer Science 2022-10-14 Philipp Holl , Vladlen Koltun , Nils Thuerey

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor generalization when the learned explanations rely on spurious…

Machine Learning · Computer Science 2024-12-11 Reza Bayat , Mohammad Pezeshki , Elvis Dohmatob , David Lopez-Paz , Pascal Vincent