English
Related papers

Related papers: Agnostic Learning of General ReLU Activation Using…

200 papers

This paper establishes risk convergence and asymptotic weight matrix alignment --- a form of implicit regularization --- of gradient flow and gradient descent when applied to deep linear networks on linearly separable data. In more detail,…

Machine Learning · Computer Science 2019-02-26 Ziwei Ji , Matus Telgarsky

Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. This paper explores the limits of this principle. Building on recent findings that the…

Machine Learning · Computer Science 2025-03-14 Damien Teney , Liangze Jiang , Florin Gogianu , Ehsan Abbasnejad

We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control…

Machine Learning · Statistics 2021-06-02 Dominic Richards , Mike Rabbat

Gaussian processes are a powerful framework for quantifying uncertainty and for sequential decision-making but are limited by the requirement of solving linear systems. In general, this has a cubic cost in dataset size and is sensitive to…

In this article we investigate blow up phenomena for gradient descent optimization methods in the training of artificial neural networks (ANNs). Our theoretical analysis is focused on shallow ANNs with one neuron on the input layer, one…

Optimization and Control · Mathematics 2022-11-29 Davide Gallon , Arnulf Jentzen , Felix Lindner

In this paper, we propose a new global analysis framework for a class of low-rank matrix recovery problems on the Riemannian manifold. We analyze the global behavior for the Riemannian optimization with random initialization. We use the…

Machine Learning · Statistics 2021-04-20 Thomas Y. Hou , Zhenzhen Li , Ziyun Zhang

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

Machine Learning · Computer Science 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external…

Machine Learning · Computer Science 2016-01-06 John Schulman , Nicolas Heess , Theophane Weber , Pieter Abbeel

In the context of over-parameterization, there is a line of work demonstrating that randomly initialized (stochastic) gradient descent (GD) converges to a globally optimal solution at a linear convergence rate for the quadratic loss…

Machine Learning · Computer Science 2025-06-16 Xianliang Xu , Ting Du , Wang Kong , Bin Shan , Ye Li , Zhongyi Huang

We derive an approximation error bound that holds simultaneously for a function and all its derivatives up to any prescribed order. The bounds apply to elementary functions, including multivariate polynomials, the exponential function, and…

Machine Learning · Computer Science 2025-12-29 Konstantin Yakovlev , Nikita Puchkin

We study dropout in two-layer neural networks with rectified linear unit (ReLU) activations. Under mild overparametrization and assuming that the limiting kernel can separate the data distribution with a positive margin, we show that…

Machine Learning · Computer Science 2020-10-27 Poorya Mianjy , Raman Arora

We establish that randomly initialized neural networks, with large width and a natural choice of hyperparameters, have nearly independent outputs exactly when their activation function is nonlinear with zero mean under the Gaussian measure:…

Machine Learning · Computer Science 2026-01-13 John Dunbar , Scott Aaronson

Despite the unresolved 'dying ReLU problem', the classical ReLU activation function (AF) has been extensively applied in Deep Neural Networks (DNN), in particular Convolutional Neural Networks (CNN), for image classification. The common…

Machine Learning · Computer Science 2021-04-30 Stamatis Mastromichalakis

Randomly initialized first-order optimization algorithms are the method of choice for solving many high-dimensional nonconvex problems in machine learning, yet general theoretical guarantees cannot rule out convergence to critical points of…

Optimization and Control · Mathematics 2018-09-28 Dar Gilboa , Sam Buchanan , John Wright

Finding the optimal configuration of parameters in ResNet is a nonconvex minimization problem, but first-order methods nevertheless find the global optimum in the overparameterized regime. We study this phenomenon with mean-field analysis,…

Machine Learning · Computer Science 2021-11-30 Zhiyan Ding , Shi Chen , Qin Li , Stephen Wright

Understanding the properties of neural networks trained via stochastic gradient descent (SGD) is at the heart of the theory of deep learning. In this work, we take a mean-field view, and consider a two-layer ReLU network trained via SGD for…

Machine Learning · Computer Science 2022-05-02 Alexander Shevchenko , Vyacheslav Kungurtsev , Marco Mondelli

Non-convex optimization problems are challenging to solve; the success and computational expense of a gradient descent algorithm or variant depend heavily on the initialization strategy. Often, either random initialization is used or…

Machine Learning · Computer Science 2020-12-23 Kartik Ahuja , Amit Dhurandhar , Kush R. Varshney

This paper concerns dictionary learning, i.e., sparse coding, a fundamental representation learning problem. We show that a subgradient descent algorithm, with random initialization, can provably recover orthogonal dictionaries on a natural…

Machine Learning · Computer Science 2019-07-02 Yu Bai , Qijia Jiang , Ju Sun

It is believed that Gradient Descent (GD) induces an implicit bias towards good generalization in training machine learning models. This paper provides a fine-grained analysis of the dynamics of GD for the matrix sensing problem, whose goal…

Machine Learning · Computer Science 2023-01-30 Jikai Jin , Zhiyuan Li , Kaifeng Lyu , Simon S. Du , Jason D. Lee

Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data. However, the generalization guarantee may not hold for noisy data. From a nonparametric perspective, this paper studies how well…

Machine Learning · Statistics 2021-09-28 Tianyang Hu , Wenjia Wang , Cong Lin , Guang Cheng