Bayesian Pool-based Active Learning With Abstention Feedbacks

2017-05-23 · Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh, Binh Nguyen

We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the classification problem and the unknown abstention rate at the same time. These are achieved by simply incorporating the estimated abstention rate into the greedy criteria. We prove that both of our algorithms have near-optimality guarantees: they respectively achieve a ${(1-\frac{1}{e})}$ constant factor approximation of the optimal expected or worst-case value of a useful utility function. Our experiments show the algorithms perform well in various practical scenarios.

📄 PDF Abstract BibTeX arXiv:1705.08481

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning General Classification

Bayesian Active Learning With Abstention Feedbacks

2019-06-04 · Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh 외

We study pool-based active learning with abstention feedbacks where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We …

Active Learning General Classification

Active Learning for Binary Classification with Abstention

2019-06-01 · Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi

We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two variants of \emph{bounded-rate} abstention, a…

Active Learning Binary Classification Classification General Classification

Exponential Savings in Agnostic Active Learning through Abstention

2021-01-31 · Nikita Puchkin, Nikita Zhivotovskiy

We show that in pool-based active classification without assumptions on the underlying distribution, if the learner is given the power to abstain from some predictions by paying the price marginally smaller than the aver…

Active Learning Classification General Classification

Bayesian Best-Arm Identification with Abstention: A Polynomial-to-Exponential Phase Transition

2026-06-28 · Yuqi Huang, Yunlong Hou, Vincent Y. F. Tan arxiv

We study the Bayesian fixed-budget best-arm identification problem in which a learner can abstain from making a terminal recommendation. Subject to an abstention budget $α$, we analyze the probability of undetected error…

Optimal Learning for Sequential Decision Making for Expensive Cost Functions with Stochastic Binary Feedbacks

2017-09-13 · Yingfei Wang, Chu Wang, Warren Powell

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attribute…

Decision Making Multi-Armed Bandits Sequential Decision Making