Active Learning with Expert Advice
Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active learning with expert advice, where the outcome of an instance is disclosed only when it is requested by the online learner. Our goal is to learn an accurate prediction model by asking the oracle the number of questions as small as possible. To address this challenge, we propose a framework of active forecasters for online active learning with expert advice, which attempts to extend two regular forecasters, i.e., Exponentially Weighted Average Forecaster and Greedy Forecaster, to tackle the task of active learning with expert advice. We prove that the proposed algorithms satisfy the Hannan consistency under some proper assumptions, and validate the efficacy of our technique by an extensive set of experiments.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningSimilar Papers 제목 키워드 기반
Fast rates for prediction with limited expert advice
We investigate the problem of minimizing the excess generalization error with respect to the best expert prediction in a finite family in the stochastic setting, under limited access to information. We assume that the le…
PredictionOnception: Active Learning with Expert Advice for Real World Machine Translation
Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Transla…
Active LearningMachine TranslationTranslationAdvice-Efficient Prediction with Expert Advice
Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited …
PredictionTeachable Reinforcement Learning via Advice Distillation
Training automated agents to complete complex tasks in interactive environments is challenging: reinforcement learning requires careful hand-engineering of reward functions, imitation learning requires specialized infras…
Decision MakingImitation Learningreinforcement-learningReinforcement Learning+1Dynamic Ensemble Active Learning: A Non-Stationary Bandit with Expert Advice
Active learning aims to reduce annotation cost by predicting which samples are useful for a human teacher to label. However it has become clear there is no best active learning algorithm. Inspired by various philosophies…
Active Learning