Structured Prediction with Stronger Consistency Guarantees

Published: 21 Sept 2023, Last Modified: 15 Jan 2024NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: structured prediction, consistency, learning theory, natural language processing
Abstract: We present an extensive study of surrogate losses for structured prediction supported by *$H$-consistency bounds*. These are recently introduced guarantees that are more relevant to learning than Bayes-consistency, since they are not asymptotic and since they take into account the hypothesis set $H$ used. We first show that no non-trivial $H$-consistency bound can be derived for widely used surrogate structured prediction losses. We then define several new families of surrogate losses, including *structured comp-sum losses* and *structured constrained losses*, for which we prove $H$-consistency bounds and thus Bayes-consistency. These loss functions readily lead to new structured prediction algorithms with stronger theoretical guarantees, based on their minimization. We describe efficient algorithms for minimizing several of these surrogate losses, including a new *structured logistic loss*.
Supplementary Material: pdf
Submission Number: 14890