paper-with-me

홈 › Papers

Structured Prediction with Stronger Consistency Guarantees

2023-09-21 · NeurIPS 2023 11

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*.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Structured Prediction Theory with Calibrated Convex Surrogate Losses

2017-03-07 · NeurIPS 2017 12 · Anton Osokin, Francis Bach, Simon Lacoste-Julien

We provide novel theoretical insights on structured prediction in the context of efficient convex surrogate loss minimization with consistency guarantees. For any task loss, we construct a convex surrogate that can be op…

PredictionStructured Prediction

Risk Guarantees for End-to-End Prediction and Optimization Processes

2020-12-30 · Nam Ho-Nguyen, Fatma Kılınç-Karzan

Prediction models are often employed in estimating parameters of optimization models. Despite the fact that in an end-to-end view, the real goal is to achieve good optimization performance, the prediction performance is …

Learning TheoryPortfolio OptimizationPrediction

Top-$k$ Classification and Cardinality-Aware Prediction

2024-03-28 · Anqi Mao, Mehryar Mohri, Yutao Zhong

We present a detailed study of top-$k$ classification, the task of predicting the $k$ most probable classes for an input, extending beyond single-class prediction. We demonstrate that several prevalent surrogate loss fun…

ClassificationMulti-class ClassificationPrediction

Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions

2026-06-22 · Sehwan Kim, Yan Sun, Faming Liang arxiv

Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their performance remain incomplete. From a statistical viewpoint, …

Image Classification

Efficient and Consistent Adversarial Bipartite Matching

2018-07-01 · ICML 2018 7 · Rizal Fathony, Sima Behpour, Xinhua Zhang, Brian Ziebart

Many important structured prediction problems, including learning to rank items, correspondence-based natural language processing, and multi-object tracking, can be formulated as weighted bipartite matching optimiza…

Computational EfficiencyLearning-To-RankMulti-Object TrackingObject Tracking+1