Agnostic Active Learning Is Always Better Than Passive Learning

NeurIPSOral2025

Authors
Steve Hanneke
Affiliation
Purdue University
Venue
NeurIPS 2025
Track
Oral

TL;DR

We prove that for every concept class, the optimal query complexity of agnostic active learning is strictly smaller than the sample complexity of agnostic passive learning.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

sample complexity

← All NeurIPS 2025 Oral papers · Browse the whole archive