Online Learning with Improving Agents: Multiclass, Budgeted Agents and Bandit Learners
Not on the map. Why?
Abstract (arXiv)
We investigate the recently introduced model of learning with improvements, where agents are allowed to make small changes to their feature values to be warranted a more desirable label. We extensively extend previously published results by providing combinatorial dimensions that characterize online learnability in this model, by analyzing the multiclass setup, learnability in a bandit feedback setup, modeling agents' cost for making improvements and more.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 17 references that are in the map. First posted on arXiv 19 Feb 2026.
Builds on
12 of 17 references.
References · 12
- 2015Strategic Classificationcited by 256
- 2019Strategic Classification is Causal Modeling in Disguisecited by 92
- 2018How Do Classifiers Induce Agents To Invest Effort Strategically?cited by 82
- 2020Causal Strategic Linear Regressioncited by 65
- 2020Maximizing Welfare with Incentive-Aware Evaluation Mechanismscited by 46
- 2022Learning Losses for Strategic Classificationcited by 22
- 2023Fundamental Bounds on Online Strategic Classificationcited by 17
- 2024Learnability Gaps of Strategic Classificationcited by 16
- 2024Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classificationcited by 8
- 2025PAC Learning with Improvementscited by 6
- 2025Should Decision-Makers Reveal Classifiers in Online Strategic Classification?cited by 5
- 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learningcited by 2
Built on by
Not cited yet.