English
Related papers

Related papers: Improved Estimation of Concentration Under $\ell_p…

200 papers

Many recent works have shown that adversarial examples that fool classifiers can be found by minimally perturbing a normal input. Recent theoretical results, starting with Gilmer et al. (2018b), show that if the inputs are drawn from a…

Machine Learning · Computer Science 2019-10-29 Saeed Mahloujifar , Xiao Zhang , Mohammad Mahmoody , David Evans

Obtaining guarantees on the convergence of the minimizers of empirical risks to the ones of the true risk is a fundamental matter in statistical learning. Instead of deriving guarantees on the usual estimation error, the goal of this paper…

Statistics Theory · Mathematics 2024-09-12 Paul Escande

A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard…

Machine Learning · Computer Science 2022-03-18 Xiao Zhang , David Evans

Concentration inequalities for the sample mean, like those due to Bernstein, Hoeffding, and Bentkus, are valid for any sample size but overly conservative, yielding confidence intervals that are unnecessarily wide. The central limit theorem…

Probability · Mathematics 2025-12-23 Morgane Austern , Lester Mackey

Dimension is an inherent bottleneck to some modern learning tasks, where optimization methods suffer from the size of the data. In this paper, we study non-isotropic distributions of data and develop tools that aim at reducing these…

Machine Learning · Statistics 2025-02-12 Mathieu Even , Laurent Massoulié

This paper gives a review of concentration inequalities which are widely employed in non-asymptotical analyses of mathematical statistics in a wide range of settings, from distribution-free to distribution-dependent, from sub-Gaussian to…

Statistics Theory · Mathematics 2025-02-24 Huiming Zhang , Song Xi Chen

Recent work in adversarial robustness suggests that natural data distributions are localized, i.e., they place high probability in small volume regions of the input space, and that this property can be utilized for designing classifiers…

Machine Learning · Computer Science 2024-05-24 Ambar Pal , René Vidal , Jeremias Sulam

The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these results can be too general to be applicable to natural data…

Machine Learning · Computer Science 2024-05-28 Ambar Pal , Jeremias Sulam , René Vidal

We study robust testing and estimation of discrete distributions in the strong contamination model. We consider both the "centralized setting" and the "distributed setting with information constraints" including communication and local…

Information Theory · Computer Science 2021-04-23 Jayadev Acharya , Ziteng Sun , Huanyu Zhang

This article studies the \emph{robust covariance matrix estimation} of a data collection $X = (x_1,\ldots,x_n)$ with $x_i = \sqrt \tau_i z_i + m$, where $z_i \in \mathbb R^p$ is a \textit{concentrated vector} (e.g., an elliptical random…

Probability · Mathematics 2022-04-12 Cosme Louart , Romain Couillet

Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and methods to measure…

Machine Learning · Computer Science 2020-03-17 Igor Buzhinsky , Arseny Nerinovsky , Stavros Tripakis

In the era of widespread public use of AI systems across various domains, ensuring adversarial robustness has become increasingly vital to maintain safety and prevent undesirable errors. Researchers have curated various adversarial datasets…

Machine Learning · Computer Science 2023-11-08 Yuanchen Bai , Raoyi Huang , Vijay Viswanathan , Tzu-Sheng Kuo , Tongshuang Wu

Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…

Computer Vision and Pattern Recognition · Computer Science 2022-05-06 Gaurav Kumar Nayak , Ruchit Rawal , Rohit Lal , Himanshu Patil , Anirban Chakraborty

We prove an extension of McDiarmid's inequality for metric spaces with unbounded diameter. To this end, we introduce the notion of the {\em subgaussian diameter}, which is a distribution-dependent refinement of the metric diameter. Our…

Probability · Mathematics 2013-09-12 Aryeh Kontorovich

The superiorization methodology is intended to work with input data of constrained minimization problems, i.e., a target function and a constraints set. However, it is based on an antipodal way of thinking to the thinking that leads…

Optimization and Control · Mathematics 2019-09-04 Yair Censor , Eliahu Levy

Compressing word embeddings is important for deploying NLP models in memory-constrained settings. However, understanding what makes compressed embeddings perform well on downstream tasks is challenging---existing measures of compression…

Machine Learning · Computer Science 2020-01-16 Avner May , Jian Zhang , Tri Dao , Christopher Ré

The concentration of measure prenomenon roughly states that, if a set $A$ in a product $\Omega^N$ of probability spaces has measure at least one half, ``most'' of the points of $\Omega^N$ are ``close'' to $A$. We proceed to a systematic…

Probability · Mathematics 2016-09-06 Michel Talagrand

One way to define the concentration of measure phenomenon is via Talagrand inequalities, also called transportation-information inequalities. That is, a comparison of the Wasserstein distance from the given measure to any other absolutely…

Probability · Mathematics 2018-11-28 Davar Khoshnevisan , Andrey Sarantsev

Adversarial attacks against deep neural networks are commonly constructed under $\ell_p$ norm constraints, most often using $p=1$, $p=2$ or $p=\infty$, and potentially regularized for specific demands such as sparsity or smoothness. These…

Machine Learning · Computer Science 2026-02-09 Christof Duhme , Florian Eilers , Xiaoyi Jiang

It is well-known that machine learning models are vulnerable to small but cleverly-designed adversarial perturbations that can cause misclassification. While there has been major progress in designing attacks and defenses for various…

Machine Learning · Computer Science 2021-04-07 Payam Delgosha , Hamed Hassani , Ramtin Pedarsani
‹ Prev 1 2 3 10 Next ›