English
Related papers

Related papers: Minimax Optimal Robust Sparse Regression with Heav…

200 papers

This paper considers the problem of asynchronous stochastic nonconvex optimization with heavy-tailed gradient noise and arbitrarily heterogeneous computation times across workers. We propose an asynchronous normalized stochastic gradient…

Optimization and Control · Mathematics 2026-01-28 Yidong Wu , Luo Luo

We consider stochastic optimization problems with heavy-tailed noise with structured density. For such problems, we show that it is possible to get faster rates of convergence than $\mathcal{O}(K^{-2(\alpha - 1)/\alpha})$, when the…

Optimization and Control · Mathematics 2024-04-18 Nikita Puchkin , Eduard Gorbunov , Nikolay Kutuzov , Alexander Gasnikov

In Online Convex Optimization (OCO), when the stochastic gradient has a finite variance, many algorithms provably work and guarantee a sublinear regret. However, limited results are known if the gradient estimate has a heavy tail, i.e., the…

Machine Learning · Computer Science 2026-03-20 Zijian Liu

Robust Bayesian methods for high-dimensional regression problems under diverse sparse regimes are studied. Traditional shrinkage priors are primarily designed to detect a handful of signals from tens of thousands of predictors in the…

Statistics Theory · Mathematics 2024-10-25 Se Yoon Lee , Peng Zhao , Debdeep Pati , Bani K. Mallick

As a fundamental problem in machine learning and differential privacy (DP), DP linear regression has been extensively studied. However, most existing methods focus primarily on either regular data distributions or low-dimensional cases with…

Machine Learning · Computer Science 2025-06-10 Xizhi Tian , Meng Ding , Touming Tao , Zihang Xiang , Di Wang

This paper studies the quantization of heavy-tailed data in some fundamental statistical estimation problems, where the underlying distributions have bounded moments of some order. We propose to truncate and properly dither the data prior…

Statistics Theory · Mathematics 2023-07-27 Junren Chen , Michael K. Ng , Di Wang

This paper studies decentralized stochastic nonconvex optimization problem over row-stochastic networks. We consider the heavy-tailed gradient noise which is empirically observed in many popular real-world applications. Specifically, we…

Optimization and Control · Mathematics 2026-01-19 Menglian Wang , Zhuanghua Liu , Luo Luo

We study random design linear regression with no assumptions on the distribution of the covariates and with a heavy-tailed response variable. In this distribution-free regression setting, we show that boundedness of the conditional second…

Statistics Theory · Mathematics 2022-02-25 Jaouad Mourtada , Tomas Vaškevičius , Nikita Zhivotovskiy

We develop two new estimators for a general class of stationary GARCH models with possibly heavy tailed asymmetrically distributed errors, covering processes with symmetric and asymmetric feedback like GARCH, Asymmetric GARCH, VGARCH and…

Statistics Theory · Mathematics 2015-07-29 Jonathan B. Hill

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

Machine Learning · Computer Science 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song

We study the problem of estimating low-rank matrices from linear measurements (a.k.a., matrix sensing) through nonconvex optimization. We propose an efficient stochastic variance reduced gradient descent algorithm to solve a nonconvex…

Machine Learning · Statistics 2017-01-17 Xiao Zhang , Lingxiao Wang , Quanquan Gu

Recent empirical evidence indicates that many machine learning applications involve heavy-tailed gradient noise, which challenges the standard assumptions of bounded variance in stochastic optimization. Gradient clipping has emerged as a…

Optimization and Control · Mathematics 2025-07-10 Florian Hübler , Ilyas Fatkhullin , Niao He

This paper introduces a simple principle for robust high-dimensional statistical inference via an appropriate shrinkage on the data. This widens the scope of high-dimensional techniques, reducing the moment conditions from sub-exponential…

Statistics Theory · Mathematics 2017-05-08 Jianqing Fan , Weichen Wang , Ziwei Zhu

In this work, we study the convergence \emph{in high probability} of clipped gradient methods when the noise distribution has heavy tails, ie., with bounded $p$th moments, for some $1<p\le2$. Prior works in this setting follow the same…

Optimization and Control · Mathematics 2023-04-05 Ta Duy Nguyen , Alina Ene , Huy L. Nguyen

We study mean change point testing problems for high-dimensional data, with exponentially- or polynomially-decaying tails. In each case, depending on the $\ell_0$-norm of the mean change vector, we separately consider dense and sparse…

Statistics Theory · Mathematics 2025-10-14 Mengchu Li , Yudong Chen , Tengyao Wang , Yi Yu

We provide a detailed study on the implicit bias of gradient descent when optimizing loss functions with strictly monotone tails, such as the logistic loss, over separable datasets. We look at two basic questions: (a) what are the…

In this paper, we study the implicit bias of gradient descent for sparse regression. We extend results on regression with quadratic parametrization, which amounts to depth-2 diagonal linear networks, to more general depth-N networks, under…

Machine Learning · Statistics 2021-10-28 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

In recent years, various notions of capacity and complexity have been proposed for characterizing the generalization properties of stochastic gradient descent (SGD) in deep learning. Some of the popular notions that correlate well with the…

Optimization and Control · Mathematics 2021-06-15 Mert Gurbuzbalaban , Umut Şimşekli , Lingjiong Zhu

In this paper, we provide novel optimal (or near optimal) convergence rates for a clipped version of the stochastic subgradient method. We consider nonsmooth convex problems over possibly unbounded domains, under heavy-tailed noise that…

Optimization and Control · Mathematics 2025-04-21 Daniela Angela Parletta , Andrea Paudice , Saverio Salzo

We propose a robust estimator for the tail index of Pareto-type distributions under random right-censoring, constructed within the minimum density power divergence (MDPD) framework and based on the Nelson--Aalen estimator of the cumulative…

Statistics Theory · Mathematics 2026-01-27 Nour Elhouda Guesmia , Abdelhakim Necir , Djamel Meraghni