English
Related papers

Related papers: How do noise tails impact on deep ReLU networks?

200 papers

The Huber loss is a robust loss function used for a wide range of regression tasks. To utilize the Huber loss, a parameter that controls the transitions from a quadratic function to an absolute value function needs to be selected. We…

Machine Learning · Statistics 2020-11-20 Gregory P. Meyer

We investigate the high-dimensional properties of robust regression estimators in the presence of heavy-tailed contamination of both the covariates and response functions. In particular, we provide a sharp asymptotic characterisation of…

Statistics Theory · Mathematics 2024-06-03 Urte Adomaityte , Leonardo Defilippis , Bruno Loureiro , Gabriele Sicuro

We study high-dimensional least-squares regression within a subgaussian statistical learning framework with heterogeneous noise. It includes $s$-sparse and $r$-low-rank least-squares regression when a fraction $\epsilon$ of the labels are…

Statistics Theory · Mathematics 2023-11-01 Philip Thompson

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

Neural networks can be trained to solve regression problems by using gradient-based methods to minimize the square loss. However, practitioners often prefer to reformulate regression as a classification problem, observing that training on…

Machine Learning · Computer Science 2023-03-02 Lawrence Stewart , Francis Bach , Quentin Berthet , Jean-Philippe Vert

We study the theory of neural network (NN) from the lens of classical nonparametric regression problems with a focus on NN's ability to adaptively estimate functions with heterogeneous smoothness -- a property of functions in Besov or…

Machine Learning · Computer Science 2024-05-21 Kaiqi Zhang , Yu-Xiang Wang

We study the fundamental problem of ReLU regression, where the goal is to fit Rectified Linear Units (ReLUs) to data. This supervised learning task is efficiently solvable in the realizable setting, but is known to be computationally hard…

Machine Learning · Computer Science 2022-01-27 Ilias Diakonikolas , Jongho Park , Christos Tzamos

Random coefficient regression models are a popular tool for analyzing unobserved heterogeneity, and have seen renewed interest in the recent econometric literature. In this paper we obtain the optimal pointwise convergence rate for…

Statistics Theory · Mathematics 2020-02-18 Hajo Holzmann , Alexander Meister

Neural network training is usually accomplished by solving a non-convex optimization problem using stochastic gradient descent. Although one optimizes over the networks parameters, the main loss function generally only depends on the…

Machine Learning · Computer Science 2023-02-10 Julius Berner , Dennis Elbrächter , Philipp Grohs

Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years. In this work, we theoretically study the importance of noise in the trajectories of gradient descent towards optimal…

Machine Learning · Computer Science 2018-07-24 Adepu Ravi Sankar , Vishwak Srinivasan , Vineeth N Balasubramanian

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári

We consider the non-parametric regression problem under Huber's $\epsilon$-contamination model, in which an $\epsilon$ fraction of observations are subject to arbitrary adversarial noise. We first show that a simple local binning median…

Statistics Theory · Mathematics 2018-05-29 Simon S. Du , Yining Wang , Sivaraman Balakrishnan , Pradeep Ravikumar , Aarti Singh

High-dimensional data subject to heavy-tailed phenomena and heterogeneity are commonly encountered in various scientific fields and bring new challenges to the classical statistical methods. In this paper, we combine the asymmetric square…

Statistics Theory · Mathematics 2019-10-02 Jun Zhao , Guan'ao Yan , Yi Zhang

This paper examines the performance of ridge regression in reproducing kernel Hilbert spaces in the presence of noise that exhibits a finite number of higher moments. We establish excess risk bounds consisting of subgaussian and polynomial…

Machine Learning · Computer Science 2025-11-07 Mattes Mollenhauer , Nicole Mücke , Dimitri Meunier , Arthur Gretton

We propose robust sparse reduced rank regression for analyzing large and complex high-dimensional data with heavy-tailed random noise. The proposed method is based on a convex relaxation of a rank- and sparsity-constrained non-convex…

Machine Learning · Statistics 2019-04-16 Kean Ming Tan , Qiang Sun , Daniela Witten

Understanding when neural networks can be learned efficiently is a fundamental question in learning theory. Existing hardness results suggest that assumptions on both the input distribution and the network's weights are necessary for…

Machine Learning · Computer Science 2023-10-05 Amit Daniely , Nathan Srebro , Gal Vardi

In this paper, we develop connections between two seemingly disparate, but central, models in robust statistics: Huber's epsilon-contamination model and the heavy-tailed noise model. We provide conditions under which this connection…

Machine Learning · Statistics 2019-07-03 Adarsh Prasad , Sivaraman Balakrishnan , Pradeep Ravikumar

Whereas recovery of the manifold from data is a well-studied topic, approximation rates for functions defined on manifolds are less known. In this work, we study a regression problem with inputs on a $d^*$-dimensional manifold that is…

Machine Learning · Statistics 2019-08-05 Johannes Schmidt-Hieber

Phase retrieval (PR) is a popular research topic in signal processing and machine learning. However, its performance degrades significantly when the measurements are corrupted by noise or outliers. To address this limitation, we propose a…

Optimization and Control · Mathematics 2025-05-30 Jun Fan , Ailing Yan , Xianchao Xiu , Wanquan Liu

We study the type of solutions to which stochastic gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. Our results are based on a dynamical stability analysis. In the…

Machine Learning · Computer Science 2023-07-03 Mor Shpigel Nacson , Rotem Mulayoff , Greg Ongie , Tomer Michaeli , Daniel Soudry