English
Related papers

Related papers: Predictor-Rejector Multi-Class Abstention: Theoret…

200 papers

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 $H$-consistency under…

Machine Learning · Computer Science 2024-07-19 Anqi Mao , Mehryar Mohri , Yutao Zhong

In this work we consider the task of constructing prediction intervals in an inductive batch setting. We present a discriminative learning framework which optimizes the expected error rate under a budget constraint on the interval sizes.…

Machine Learning · Computer Science 2018-02-28 Nir Rosenfeld , Yishay Mansour , Elad Yom-Tov

We study active learning where the labeler can not only return incorrect labels but also abstain from labeling. We consider different noise and abstention conditions of the labeler. We propose an algorithm which utilizes abstention…

Machine Learning · Computer Science 2016-11-01 Songbai Yan , Kamalika Chaudhuri , Tara Javidi

Discrimination-aware classification is receiving an increasing attention in data science fields. The pre-process methods for constructing a discrimination-free classifier first remove discrimination from the training data, and then learn…

Machine Learning · Computer Science 2018-03-30 Lu Zhang , Yongkai Wu , Xintao Wu

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold…

Machine Learning · Computer Science 2026-05-26 Hen Davidov , Nachshon Cohen , Oren Kalinsky , Yaron Fairstein , Guy Kushilevitz , Ram Yazdi , Patrick Rebeschini

Learning algorithms are often used in conjunction with expert decision makers in practical scenarios, however this fact is largely ignored when designing these algorithms. In this paper we explore how to learn predictors that can either…

Machine Learning · Computer Science 2021-01-26 Hussein Mozannar , David Sontag

We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option. Existing rejection mechanisms are based mostly…

Machine Learning · Computer Science 2019-06-28 Yonatan Geifman , Ran El-Yaniv

We study online learning in the adversarial injection model introduced by [Goel et al. 2017], where a stream of labeled examples is predominantly drawn i.i.d.\ from an unknown distribution $\mathcal{D}$, but may be interspersed with…

Machine Learning · Computer Science 2026-02-24 Ezra Edelman , Surbhi Goel

Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework…

Robotics · Computer Science 2025-09-23 Divake Kumar , Nastaran Darabi , Sina Tayebati , Amit Ranjan Trivedi

Abstention, the refusal of large language models (LLMs) to provide an answer, is increasingly recognized for its potential to mitigate hallucinations and enhance safety in LLM systems. In this survey, we introduce a framework to examine…

Computation and Language · Computer Science 2025-02-13 Bingbing Wen , Jihan Yao , Shangbin Feng , Chenjun Xu , Yulia Tsvetkov , Bill Howe , Lucy Lu Wang

We study the binary hypothesis testing problem where an adversary may potentially corrupt a fraction of the samples. The detector is, however, permitted to abstain from making a decision if (and only if) the adversary is present. We…

Information Theory · Computer Science 2025-01-24 Malhar A. Managoli , K. R. Sahasranand , Vinod M. Prabhakaran

In critical applications, it is vital for classifiers to defer decision-making to humans. We propose a post-hoc method that makes existing classifiers selectively abstain from predicting certain samples. Our abstaining classifier is…

Machine Learning · Computer Science 2023-10-11 Tongxin Yin , Jean-François Ton , Ruocheng Guo , Yuanshun Yao , Mingyan Liu , Yang Liu

Abstaining classificaiton aims to reject to classify the easily misclassified examples, so it is an effective approach to increase the clasificaiton reliability and reduce the misclassification risk in the cost-sensitive applications. In…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Hongjiao Guan , Yingtao Zhang , H. D. Cheng , Xianglong Tang

We consider the learning--unlearning paradigm defined as follows. First given a dataset, the goal is to learn a good predictor, such as one minimizing a certain loss. Subsequently, given any subset of examples that wish to be unlearnt, the…

Machine Learning · Computer Science 2023-06-29 Badih Ghazi , Pritish Kamath , Ravi Kumar , Pasin Manurangsi , Ayush Sekhari , Chiyuan Zhang

Optimization models used to make discrete decisions often contain uncertain parameters that are context-dependent and estimated through prediction. To account for the quality of the decision made based on the prediction, decision-focused…

Machine Learning · Computer Science 2024-07-30 Noah Schutte , Krzysztof Postek , Neil Yorke-Smith

Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing…

Machine Learning · Computer Science 2025-09-29 Natalie S. Frank

This paper proposes a novel non-intrusive system failure prediction technique using available information from developers and minimal information from raw logs (rather than mining entire logs) but keeping the data entirely private with the…

Artificial Intelligence · Computer Science 2024-09-20 Dibakar Das , Vikram Seshasai , Vineet Sudhir Bhat , Pushkal Juneja , Jyotsna Bapat , Debabrata Das

Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selecting an expert,…

Machine Learning · Statistics 2026-05-29 Yannis Montreuil , Leïna Montreuil , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi

We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes optimal classifier for an arbitrary input-label distribution…

Machine Learning · Computer Science 2019-05-24 Shubhanshu Shekhar , Mohammad Ghavamzadeh , Tara Javidi

We investigate the problem of regression where one is allowed to abstain from predicting. We refer to this framework as regression with reject option as an extension of classification with reject option. In this context, we focus on the…

Machine Learning · Statistics 2021-03-08 Christophe Denis , Mohamed Hebiri , Ahmed Zaoui