Consistency Conditions for Differentiable Surrogate Losses
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Universal Growth Rate for Learning with Smooth Surrogate Losses
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 ClassificationRealizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
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
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 RobustnessLinear-Core Surrogates: Smooth Loss Functions with Linear Rates for Classification and Structured Prediction
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 PredictionCalibrated Surrogate Losses for Adversarially Robust Classification
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