The Adversarial Consistency of Surrogate Risks for Binary Classification

Authors: Natalie Frank, Jonathan Niles-Weed

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We give a simple and complete characterization of the set of surrogate loss functions that are consistent... We also prove a quantitative version of adversarial consistency for the -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.
Researcher Affiliation Academia Natalie S. Frank Courant Institute New York University New York, NY 10012 nf1066@nyu.edu Jonathan Niles-Weed Courant Institute New York University New York, NY 10012 jnw@cims.nyu.edu
Pseudocode No The paper does not contain any pseudocode or algorithm blocks. It focuses on theoretical proofs and mathematical derivations.
Open Source Code No The paper does not provide any statement or link regarding the release of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not describe experiments using datasets. No dataset is mentioned as publicly available.
Dataset Splits No The paper is theoretical and does not describe any dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any experimental setup involving specific hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any experimental setup involving specific software dependencies or versions.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, hyperparameters, or training configurations.