English
Related papers

Related papers: The Adversarial Consistency of Surrogate Risks for…

200 papers

Robustness to adversarial perturbations is of paramount concern in modern machine learning. One of the state-of-the-art methods for training robust classifiers is adversarial training, which involves minimizing a supremum-based surrogate…

Machine Learning · Computer Science 2023-05-18 Natalie S. Frank , Jonathan Niles-Weed

A central concern in classification is the vulnerability of machine learning models to adversarial attacks. Adversarial training is one of the most popular techniques for training robust classifiers, which involves minimizing an adversarial…

Machine Learning · Computer Science 2025-10-09 Natalie S. Frank

Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing…

Machine Learning · Computer Science 2025-09-29 Natalie S. Frank

In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a proxy for minimizing the $0/1$ loss in the presence of an…

Machine Learning · Computer Science 2022-05-23 Laurent Meunier , Raphaël Ettedgui , Rafael Pinot , Yann Chevaleyre , Jamal Atif

Adversarial training is one of the most popular methods for training methods robust to adversarial attacks, however, it is not well-understood from a theoretical perspective. We prove and existence, regularity, and minimax theorems for…

Machine Learning · Computer Science 2025-10-09 Natalie S. Frank , Jonathan Niles-Weed

Adversarially robust classification seeks a classifier that is insensitive to adversarial perturbations of test patterns. This problem is often formulated via a minimax objective, where the target loss is the worst-case value of the 0-1…

Machine Learning · Statistics 2021-05-14 Han Bao , Clayton Scott , Masashi Sugiyama

Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the adversarial loss with most hypothesis sets is NP-hard. But…

Machine Learning · Computer Science 2021-05-05 Pranjal Awasthi , Natalie Frank , Anqi Mao , Mehryar Mohri , Yutao Zhong

We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case…

In machine learning, the loss functions optimized during training often differ from the target loss that defines task performance due to computational intractability or lack of differentiability. We present an in-depth study of the target…

Machine Learning · Computer Science 2025-12-30 Yutao Zhong

Robustness towards adversarial attacks is a vital property for classifiers in several applications such as autonomous driving, medical diagnosis, etc. Also, in such scenarios, where the cost of misclassification is very high, knowing when…

Machine Learning · Computer Science 2024-10-15 Vrund Shah , Tejas Chaudhari , Naresh Manwani

When minimizing the empirical risk in binary classification, it is a common practice to replace the zero-one loss with a surrogate loss to make the learning objective feasible to optimize. Examples of well-known surrogate losses for binary…

Machine Learning · Statistics 2023-06-07 Nontawat Charoenphakdee , Jongyeong Lee , Masashi Sugiyama

Commonly used classification algorithms in machine learning, such as support vector machines, minimize a convex surrogate loss on training examples. In practice, these algorithms are surprisingly robust to errors in the training data. In…

Machine Learning · Computer Science 2020-12-03 Kunal Talwar

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed…

Machine Learning · Computer Science 2014-02-11 Mehrdad Mahdavi , Lijun Zhang , Rong Jin

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be optimized via…

Machine Learning · Computer Science 2018-01-30 Anton Osokin , Francis Bach , Simon Lacoste-Julien

We present a comprehensive study of surrogate loss functions for learning to defer. We introduce a broad family of surrogate losses, parameterized by a non-increasing function $\Psi$, and establish their realizable $H$-consistency under…

Machine Learning · Computer Science 2024-07-19 Anqi Mao , Mehryar Mohri , Yutao Zhong

We study consistency properties of machine learning methods based on minimizing convex surrogates. We extend the recent framework of Osokin et al. (2017) for the quantitative analysis of consistency properties to the case of inconsistent…

Machine Learning · Computer Science 2019-01-10 Kirill Struminsky , Simon Lacoste-Julien , Anton Osokin

Many of the ordinal regression models that have been proposed in the literature can be seen as methods that minimize a convex surrogate of the zero-one, absolute, or squared loss functions. A key property that allows to study the…

Machine Learning · Computer Science 2017-07-24 Fabian Pedregosa , Francis Bach , Alexandre Gramfort

The goal of binary classification is to estimate a discriminant function $\gamma$ from observations of covariate vectors and corresponding binary labels. We consider an elaboration of this problem in which the covariates are not available…

Statistics Theory · Mathematics 2009-09-29 XuanLong Nguyen , Martin J. Wainwright , Michael I. Jordan

Adversarially robust learning aims to design algorithms that are robust to small adversarial perturbations on input variables. Beyond the existing studies on the predictive performance to adversarial samples, our goal is to understand…

Machine Learning · Statistics 2020-12-21 Yue Xing , Ruizhi Zhang , Guang Cheng

It has been consistently reported that many machine learning models are susceptible to adversarial attacks i.e., small additive adversarial perturbations applied to data points can cause misclassification. Adversarial training using…

Machine Learning · Statistics 2021-07-15 Hossein Taheri , Ramtin Pedarsani , Christos Thrampoulidis
‹ Prev 1 2 3 10 Next ›