paper-with-me

홈 › Papers

The Adversarial Consistency of Surrogate Risks for Binary Classification

2023-05-17 · NeurIPS 2023 11 · Natalie Frank, Jonathan Niles-Weed

We study the consistency of surrogate risks for robust binary classification. It is common to learn robust classifiers by adversarial training, which seeks to minimize the expected $0$-$1$ loss when each example can be maliciously corrupted within a small ball. We give a simple and complete characterization of the set of surrogate loss functions that are \emph{consistent}, i.e., that can replace the $0$-$1$ loss without affecting the minimizing sequences of the original adversarial risk, for any data distribution. We also prove a quantitative version of adversarial consistency for the $\rho$-margin loss. Our results reveal that the class of adversarially consistent surrogates is substantially smaller than in the standard setting, where many common surrogates are known to be consistent.

📄 PDF Abstract BibTeX arXiv:2305.09956

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationClassification

Similar Papers 제목 키워드 기반

The Consistency of Adversarial Training for Binary Classification

2022-06-18 · Natalie S. Frank, Jonathan Niles-Weed

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 supremu…

BIG-bench Machine LearningBinary ClassificationClassification

Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification

2022-06-18 · Natalie S. Frank, Jonathan Niles-Weed

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 minim…

Adversarial RobustnessBinary Classification

Adversarial Surrogate Risk Bounds for Binary Classification

2025-06-11 · Natalie S. Frank

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 minim…

Binary ClassificationClassification

Fundamental Novel Consistency Theory: $H$-Consistency Bounds

2025-12-28 · Yutao Zhong arxiv

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 s…

Multi-class ClassificationBinary Classification

Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier

2024-04-26 · 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 wo…

Classification