English
Related papers

Related papers: Robust mean estimation under star-shaped constrain…

200 papers

We study stochastic nonconvex optimization under heavy-tailed noise. In this setting, the stochastic gradients only have bounded $p$-th central moment ($p$-BCM) for some $p \in (1,2]$. Building on the foundational work of Arjevani et al.…

Optimization and Control · Mathematics 2026-04-01 Adrien Fradin , Abdurakhmon Sadiev , Laurent Condat , Peter Richtárik

Machine learning algorithms in high-dimensional settings are highly susceptible to the influence of even a small fraction of structured outliers, making robust optimization techniques essential. In particular, within the…

Machine Learning · Computer Science 2025-04-25 Changyu Gao , Andrew Lowy , Xingyu Zhou , Stephen J. Wright

We establish maximal concentration bounds for the iterates generated by stochastic approximation algorithms with general step sizes, where the noise has a finite-state Markovian component plus a Martingale-difference component. When the…

Probability · Mathematics 2026-05-21 Shubhada Agrawal , Siva Theja Maguluri , Martin Zubeldia

We study mean estimation of a random vector $X$ in a distributed parameter-server-worker setup. Worker $i$ observes samples of $a_i^\top X$, where $a_i^\top$ is the $i$th row of a known sensing matrix $A$. The key challenges are adversarial…

In data-driven learning and inference tasks, the high cost of acquiring samples from the target distribution often limits performance. A common strategy to mitigate this challenge is to augment the limited target samples with data from a…

Statistics Theory · Mathematics 2025-02-06 Barron Han , Danil Akhtiamov , Reza Ghane , Babak Hassibi

Dynamical systems can confront one of two extreme types of disturbances: persistent zero-mean independent noise, and sparse nonzero-mean adversarial attacks, depending on the specific scenario being modeled. While mean-based estimators like…

Optimization and Control · Mathematics 2026-03-31 Jihun Kim , Javad Lavaei

Identifying anomalies and contamination in datasets is important in a wide variety of settings. In this paper, we describe a new technique for estimating contamination in large, discrete valued datasets. Our approach considers the normal…

Information Theory · Computer Science 2015-06-16 Matthew L. Malloy , Scott Alfeld , Paul Barford

We study theoretical properties of regularized robust M-estimators, applicable when data are drawn from a sparse high-dimensional linear model and contaminated by heavy-tailed distributions and/or outliers in the additive errors and…

Statistics Theory · Mathematics 2015-01-05 Po-Ling Loh

We develop a probabilistic method for assessing the tail behavior and geometric stability of one-dimensional n i.i.d. samples by tracking how their span contracts when the most extreme points are trimmed. Central to our approach is the…

Machine Learning · Statistics 2025-09-03 Erwan Dereure , Emmanuel Akame Mfoumou , David Holcman

Determining the sound speed $c_s$ in compact stars is an important open question with numerous implications on the behaviour of matter at large densities and hence on gravitational-wave emission from neutron stars. To this scope, we…

High Energy Astrophysical Phenomena · Physics 2022-12-07 Sinan Altiparmak , Christian Ecker , Luciano Rezzolla

We consider an $\ell_2$-regularized non-convex optimization problem for recovering signals from their noisy phaseless observations. We design and study the performance of a message passing algorithm that aims to solve this optimization…

Information Theory · Computer Science 2018-06-11 Junjie Ma , Ji Xu , Arian Maleki

Heavy-tailed errors impair the accuracy of the least squares estimate, which can be spoiled by a single grossly outlying observation. As argued in the seminal work of Peter Huber in 1973 [{\it Ann. Statist.} {\bf 1} (1973) 799--821], robust…

Statistics Theory · Mathematics 2017-11-16 Wen-Xin Zhou , Koushiki Bose , Jianqing Fan , Han Liu

We investigate stable recovery guarantees for phase retrieval under two realistic and challenging noise models: the Poisson model and the heavy-tailed model. Our analysis covers both nonconvex least squares (NCVX-LS) and convex least…

Statistics Theory · Mathematics 2025-10-02 Gao Huang , Song Li , Deanna Needell

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm…

Machine Learning · Computer Science 2025-02-10 Sreejeet Maity , Aritra Mitra

This paper introduces a general regularized thresholded least-square procedure estimating a structured signal $\theta_*\in\mathbb{R}^d$ from the following observations: $y_i = f(\langle\mathbf{x}_i, \theta_*\rangle,…

Statistics Theory · Mathematics 2018-04-18 Xiaohan Wei

Change point detection is becoming increasingly popular in many application areas. On one hand, most of the theoretically-justified methods are investigated in an ideal setting without model violations, or merely robust against identical…

Methodology · Statistics 2021-10-26 Mengchu Li , Yi Yu

We analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}_{p,r}$ as the best robust classification error achieved by a halfspace that is…

Machine Learning · Computer Science 2021-04-20 Difan Zou , Spencer Frei , Quanquan Gu

We consider the stochastic optimization problem with smooth but not necessarily convex objectives in the heavy-tailed noise regime, where the stochastic gradient's noise is assumed to have bounded $p$th moment ($p\in(1,2]$). Zhang et al.…

Machine Learning · Computer Science 2023-09-06 Zijian Liu , Jiawei Zhang , Zhengyuan Zhou

We study the problem of linear regression where both covariates and responses are potentially (i) heavy-tailed and (ii) adversarially contaminated. Several computationally efficient estimators have been proposed for the simpler setting…

Statistics Theory · Mathematics 2021-05-18 Ankit Pensia , Varun Jog , Po-Ling Loh

We study Empirical Risk Minimizers (ERM) and Regularized Empirical Risk Minimizers (RERM) for regression problems with convex and $L$-Lipschitz loss functions. We consider a setting where $|\cO|$ malicious outliers contaminate the labels.…

Statistics Theory · Mathematics 2020-09-28 Geoffrey Chinot
‹ Prev 1 4 5 6 7 8 10 Next ›