mlsanityData to 7 Oct 2026

Discriminative Feature Feedback with General Teacher Classes

arXiv 2510.07245 ↗First posted 8 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We study the theoretical properties of the interactive learning protocol Discriminative Feature Feedback (DFF) (Dasgupta et al., 2018). The DFF learning protocol uses feedback in the form of discriminative feature explanations. We provide the first systematic study of DFF in a general framework that is comparable to that of classical protocols such as supervised learning and online learning. We study the optimal mistake bound of DFF in the realizable and the non-realizable settings, and obtain novel structural results, as well as insights into the differences between Online Learning and settings with richer feedback such as DFF. We characterize the mistake bound in the realizable setting using a new notion of dimension. In the non-realizable setting, we provide a mistake upper bound and show that it cannot be improved in general. Our results show that unlike Online Learning, in DFF the realizable dimension is insufficient to characterize the optimal non-realizable mistake bound or the existence of no-regret algorithms.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 34 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

11 of 34 references.

References · 11

  1. 2022Can language models learn from explanations in context?cited by 248
  2. 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 141
  3. 2020A Theory of Universal Learningcited by 59
  4. 2021Adversarial Laws of Large Numbers and Optimal Regret in Online Classificationcited by 39
  5. 2020ALICE: Active Learning with Contrastive Natural Language Explanationscited by 36
  6. 2018Teaching Categories to Human Learners with Visual Explanationscited by 30
  7. 2023Optimal Prediction Using Expert Advice and Randomized Littlestone Dimensioncited by 18
  8. 2021Online Selective Classification with Limited Feedbackcited by 8
  9. 2020Robust Learning from Discriminative Feature Feedbackcited by 7
  10. 2015Crowdsourcing Feature Discovery via Adaptively Chosen Comparisonscited by 5
  11. 2022Improved Robust Algorithms for Learning with Discriminative Feature Feedbackcited by 1

Built on by

Not cited yet.