paper-with-me

Papers

Consistency Conditions for Differentiable Surrogate Losses

2025-05-19 · Drona Khurana, Anish Thilagar, Dhamma Kimpara, Rafael Frongillo

The statistical consistency of surrogate losses for discrete prediction tasks is often checked via the condition of calibration. However, directly verifying calibration can be arduous. Recent work shows that for polyhedral surrogates, a less arduous condition, indirect elicitation (IE), is still equivalent to calibration. We give the first results of this type for non-polyhedral surrogates, specifically the class of convex differentiable losses. We first prove that under mild conditions, IE and calibration are equivalent for one-dimensional losses in this class. We construct a counter-example that shows that this equivalence fails in higher dimensions. This motivates the introduction of strong IE, a strengthened form of IE that is equally easy to verify. We establish that strong IE implies calibration for differentiable surrogates and is both necessary and sufficient for strongly convex, differentiable surrogates. Finally, we apply these results to a range of problems to demonstrate the power of IE and strong IE for designing and analyzing consistent differentiable surrogates.

📄 PDF Abstract BibTeX arXiv:2505.13760

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Universal Growth Rate for Learning with Smooth Surrogate Losses

2024-05-09 · Anqi Mao, Mehryar Mohri, Yutao Zhong

This paper presents a comprehensive analysis of the growth rate of $H$-consistency bounds (and excess error bounds) for various surrogate losses used in classification. We prove a square-root growth rate near zero for sm…

Binary ClassificationClassificationMulti-class Classification

Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer

2024-07-18 · Anqi Mao, Mehryar Mohri, Yutao Zhong

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 $H$-c…

Calibration and Consistency of Adversarial Surrogate Losses

2021-04-19 · NeurIPS 2021 12 · Pranjal Awasthi, Natalie Frank, Anqi Mao, Mehryar Mohri 외

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 s…

Adversarial Robustness

Linear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction

2026-04-30 · Mehryar Mohri, Yutao Zhong arxiv

The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while piecewise-linear loss…

Structured Prediction

Calibrated Surrogate Losses for Adversarially Robust Classification

2020-05-28 · Han Bao, Clayton Scott, Masashi Sugiyama

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 …

ClassificationGeneral ClassificationRobust classification