AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Achieving Minimax Rates in Pool-Based Batch Active Learning

Claudio Gentile, Zhilei Wang, Tong Zhang

ICML 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Deep active learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Stage-wise greedy G-optimal design with pseudo-labeling (Algorithm 1) for linear models, versus standard batch/passive baselinespool-based batch active learning, linear models · theoretical analysis, noisy linear model under low-noise conditionexcess risk vs label complexityImproved
Constant batch size B reduced to as small as T^(2/(α+2)) instead of unbounded batch sizeconstant-batch variant of Algorithm 1 · theoretical analysis, linear modelsexcess risk vs label complexity (minimax rate)No clear effect
Number of re-training stages kept at most logarithmic in pool size, automatically adapting to noise levelAlgorithm 1 · theoretical analysis, linear modelsnumber of stages LImproved
Logistic-model extension with regularized logistic regression estimators and exponentially shrinking margin regionsAlgorithm 2 (logistic case) · theoretical analysis, generalized linear logistic modelexcess risk bound dependence on input dimension dHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy