English
Related papers

Related papers: Implicit Bias of MSE Gradient Optimization in Unde…

200 papers

We study the training dynamics of a shallow neural network with quadratic activation functions and quadratic cost in a teacher-student setup. In line with previous works on the same neural architecture, the optimization is performed…

Optimization and Control · Mathematics 2023-11-08 Simon Martin , Francis Bach , Giulio Biroli

Recent works have shown that traditional Neural Network (NN) architectures display a marked frequency bias in the learning process. Namely, the NN first learns the low-frequency features before learning the high-frequency ones. In this…

Machine Learning · Computer Science 2024-05-27 Juan Molina , Mircea Petrache , Francisco Sahli Costabal , Matías Courdurier

Understanding the training dynamics of deep neural networks remains a major open problem, with physics-inspired approaches offering promising insights. Building on this perspective, we develop a thermodynamic framework to describe the…

Machine Learning · Computer Science 2026-05-15 Ildus Sadrtdinov , Ekaterina Lobacheva , Ivan Klimov , Mikhail Burtsev , Mikhail I. Katsnelson , Dmitry Vetrov

The design of a neural image compression network is governed by how well the entropy model matches the true distribution of the latent code. Apart from the model capacity, this ability is indirectly under the effect of how close the relaxed…

Image and Video Processing · Electrical Eng. & Systems 2023-09-21 Ali Zafari , Atefeh Khoshkhahtinat , Piyush Mehta , Mohammad Saeed Ebrahimi Saadabadi , Mohammad Akyash , Nasser M. Nasrabadi

In this article, we review the literature on statistical theories of neural networks from three perspectives: approximation, training dynamics and generative models. In the first part, results on excess risks for neural networks are…

Machine Learning · Statistics 2024-09-17 Namjoon Suh , Guang Cheng

This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constraints that require the objectives across the network to lie in…

Multiagent Systems · Computer Science 2020-04-22 Roula Nassif , Stefan Vlaski , Ali H. Sayed

We study the high-dimensional training dynamics of a shallow neural network with quadratic activation in a teacher-student setup. We focus on the extensive-width regime, where the teacher and student network widths scale proportionally with…

Optimization and Control · Mathematics 2026-01-16 Simon Martin , Giulio Biroli , Francis Bach

The adversarial vulnerability of neural nets, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon. Here, we study adversarial examples of trained…

Machine Learning · Computer Science 2023-02-01 Nikolaos Tsilivis , Julia Kempe

Bounds on the smallest eigenvalue of the neural tangent kernel (NTK) are a key ingredient in the analysis of neural network optimization and memorization. However, existing results require distributional assumptions on the data and are…

Machine Learning · Statistics 2024-05-24 Kedar Karhadkar , Michael Murray , Guido Montúfar

We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in…

Training data privacy is a fundamental problem in modern Artificial Intelligence (AI) applications, such as face recognition, recommendation systems, language generation, and many others, as it may contain sensitive user information related…

Machine Learning · Computer Science 2024-11-05 Jiuxiang Gu , Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song

Are neural networks biased toward simple functions? Does depth always help learn more complex features? Is training the last layer of a network as good as training all layers? How to set the range for learning rate tuning? These questions…

Machine Learning · Computer Science 2020-04-10 Greg Yang , Hadi Salman

Recently, researchers proposed various low-precision gradient compression, for efficient communication in large-scale distributed optimization. Based on these work, we try to reduce the communication complexity from a new direction. We…

Machine Learning · Computer Science 2019-01-25 Jianqiao Wangni , Ke Li , Jianbo Shi , Jitendra Malik

We perform an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant "high-dimensional" regime where the number of free parameters in the network is on…

Machine Learning · Statistics 2017-10-11 Madhu S. Advani , Andrew M. Saxe

Pruning neural networks before training has received increasing interest due to its potential to reduce training time and memory. One popular method is to prune the connections based on a certain metric, but it is not entirely clear what…

Machine Learning · Computer Science 2023-04-07 Yite Wang , Dawei Li , Ruoyu Sun

A fairly comprehensive analysis is presented for the gradient descent dynamics for training two-layer neural network models in the situation when the parameters in both layers are updated. General initialization schemes as well as general…

Machine Learning · Computer Science 2020-02-27 Weinan E , Chao Ma , Lei Wu

Deep neural networks are usually trained with stochastic gradient descent (SGD), which minimizes objective function using very rough approximations of gradient, only averaging to the real gradient. Standard approaches like momentum or ADAM…

Machine Learning · Computer Science 2023-03-14 Jarek Duda

A convergence analysis is developed for the regularized Newton method for training neural networks (NNs) in the overparameterized limit. As the number of hidden units tends to infinity, the NN training dynamics converge in probability to…

Machine Learning · Computer Science 2026-05-21 Konstantin Riedl , Konstantinos Spiliopoulos , Justin Sirignano

The Koopman operator provides a principled framework for analyzing nonlinear dynamical systems through linear operator theory. Recent advances in dynamic mode decomposition (DMD) have shown that trajectory data can be used to identify…

Machine Learning · Computer Science 2026-01-21 Minchan Jeong , J. Jon Ryu , Se-Young Yun , Gregory W. Wornell

In this work, we analyze the optimization dynamics of generative fine-tuning. We observe that under the Flow Matching framework, the standard MSE objective can be formulated as a Quadratic Form governed by a dynamically evolving Neural…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Zhinan Xiong , Shunqi Yuan