paper-with-me

Papers

Adaptive Selective Sampling for Online Prediction with Experts

2023-02-16 · NeurIPS 2023 11

We consider online prediction of a binary sequence with expert advice. For this setting, we devise label-efficient forecasting algorithms, which use a selective sampling scheme that enables collecting much fewer labels than standard procedures, while still retaining optimal worst-case regret guarantees. These algorithms are based on exponentially weighted forecasters, suitable for settings with and without a perfect expert. For a scenario where one expert is strictly better than the others in expectation, we show that the label complexity of the label-efficient forecaster scales roughly as the square root of the number of rounds. Finally, we present numerical experiments empirically showing that the normalized regret of the label-efficient forecaster can asymptotically match known minimax rates for pool-based active learning, suggesting it can optimally adapt to benign settings.

📄 PDF Abstract BibTeX arXiv:2302.08397

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningPrediction

Similar Papers 제목 키워드 기반

A Regret-Variance Trade-Off in Online Learning

2022-06-06 · Dirk van der Hoeven, Nikita Zhivotovskiy, Nicolò Cesa-Bianchi

We consider prediction with expert advice for strongly convex and bounded losses, and investigate trade-offs between regret and "variance" (i.e., squared difference of learner's predictions and best expert predictions). …

Model Selection

Online selective conformal inference: adaptive scores, convergence rate and optimality

2025-08-14 · Pierre Humbert, Ulysse Gazin, Ruth Heller, Etienne Roquain arxiv

In a supervised online setting, quantifying uncertainty has been proposed in the seminal work of \cite{gibbs2021adaptive}. For any given point-prediction algorithm, their method (ACI) produces a conformal prediction set …

Selective Sampling with Drift

2014-02-17 · Edward Moroshko, Koby Crammer

Recently there has been much work on selective sampling, an online active learning setting, in which algorithms work in rounds. On each round an algorithm receives an input and makes a prediction. Then, it can decide whe…

Active Learning

Streaming Algorithms for Learning with Experts: Deterministic Versus Robust

2023-03-03 · David P. Woodruff, Fred Zhang, Samson Zhou

In the online learning with experts problem, an algorithm must make a prediction about an outcome on each of $T$ days (or times), given a set of $n$ experts who make predictions on each day (or time). The algorithm is gi…

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation

2024-02-13 · Daeun Lee, Jaehong Yoon, Sung Ju Hwang

Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy t…

Test-time Adaptation