English
Related papers

Related papers: Eigenvalue Decay Implies Polynomial-Time Learnabil…

200 papers

How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory…

Machine Learning · Computer Science 2019-05-28 Zeyuan Allen-Zhu , Yuanzhi Li , Zhao Song

We draw connections between simple neural networks and under-determined linear systems to comprehensively explore several interesting theoretical questions in the study of neural networks. First, we emphatically show that it is unsurprising…

Numerical Analysis · Mathematics 2020-11-02 Austin R. Benson , Anil Damle , Alex Townsend

We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives…

Data Structures and Algorithms · Computer Science 2025-02-25 Gautam Chandrasekaran , Adam R. Klivans , Lin Lin Lee , Konstantinos Stavropoulos

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

We consider the dynamic of gradient descent for learning a two-layer neural network. We assume the input $x\in\mathbb{R}^d$ is drawn from a Gaussian distribution and the label of $x$ satisfies $f^{\star}(x) = a^{\top}|W^{\star}x|$, where…

Machine Learning · Computer Science 2020-07-10 Yuanzhi Li , Tengyu Ma , Hongyang R. Zhang

We consider the problem of finding a two-layer neural network with sigmoid, rectified linear unit (ReLU), or binary step activation functions that "fits" a training data set as accurately as possible as quantified by the training error; and…

Machine Learning · Statistics 2022-04-06 David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

In this work, we demonstrate provable guarantees on the training of a single ReLU gate in hitherto unexplored regimes. We give a simple iterative stochastic algorithm that can train a ReLU gate in the realizable setting in linear time while…

Machine Learning · Computer Science 2022-04-04 Sayar Karmakar , Anirbit Mukherjee

We consider the fundamental problem of ReLU regression, where the goal is to output the best fitting ReLU with respect to square loss given access to draws from some unknown distribution. We give the first efficient, constant-factor…

Machine Learning · Computer Science 2020-09-30 Ilias Diakonikolas , Surbhi Goel , Sushrut Karmalkar , Adam R. Klivans , Mahdi Soltanolkotabi

We investigate the complexity of training a two-layer ReLU neural network with weight decay regularization. Previous research has shown that the optimal solution of this problem can be found by solving a standard cone-constrained convex…

Machine Learning · Computer Science 2023-11-21 Yifei Wang , Mert Pilanci

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

The first provably efficient algorithm for learning graph neural networks (GNNs) with one hidden layer for node information convolution is provided in this paper. Two types of GNNs are investigated, depending on whether labels are attached…

Machine Learning · Computer Science 2020-12-08 Qunwei Li , Shaofeng Zou , Wenliang Zhong

In this article we study fully-connected feedforward deep ReLU ANNs with an arbitrarily large number of hidden layers and we prove convergence of the risk of the GD optimization method with random initializations in the training of such…

Optimization and Control · Mathematics 2022-07-14 Arnulf Jentzen , Adrian Riekert

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

There has been a large amount of interest, both in the past and particularly recently, into the power of different families of universal approximators, e.g. ReLU networks, polynomials, rational functions. However, current research has…

Machine Learning · Computer Science 2018-05-30 Frederic Koehler , Andrej Risteski

Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate of contraction…

Optimization and Control · Mathematics 2024-06-07 Aaron Fainman , Stefan Vlaski

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

We develop exact representations of training two-layer neural networks with rectified linear units (ReLUs) in terms of a single convex program with number of variables polynomial in the number of training samples and the number of hidden…

Machine Learning · Computer Science 2020-08-18 Mert Pilanci , Tolga Ergen

In studying the expressiveness of neural networks, an important question is whether there are functions which can only be approximated by sufficiently deep networks, assuming their size is bounded. However, for constant depths, existing…

Machine Learning · Computer Science 2020-12-29 Gal Vardi , Ohad Shamir