# Discriminative Feature Feedback with General Teacher Classes

arXiv: https://arxiv.org/abs/2510.07245 · HTML: https://mlsanity.com/paper/2510.07245/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Making deep neural networks right for the right scientific reasons by interacting with their explanations](https://mlsanity.com/paper/2001.05371/) (2020)
- [A Theory of Universal Learning](https://mlsanity.com/paper/2011.04483/) (2020)
- [Adversarial Laws of Large Numbers and Optimal Regret in Online Classification](https://mlsanity.com/paper/2101.09054/) (2021)
- [ALICE: Active Learning with Contrastive Natural Language Explanations](https://mlsanity.com/paper/2009.10259/) (2020)
- [Teaching Categories to Human Learners with Visual Explanations](https://mlsanity.com/paper/1802.06924/) (2018)
- [Optimal Prediction Using Expert Advice and Randomized Littlestone Dimension](https://mlsanity.com/paper/2302.13849/) (2023)
- [Online Selective Classification with Limited Feedback](https://mlsanity.com/paper/2110.14243/) (2021)
- [Robust Learning from Discriminative Feature Feedback](https://mlsanity.com/paper/2003.03946/) (2020)
- [Crowdsourcing Feature Discovery via Adaptively Chosen Comparisons](https://mlsanity.com/paper/1504.00064/) (2015)
- [Improved Robust Algorithms for Learning with Discriminative Feature Feedback](https://mlsanity.com/paper/2209.03753/) (2022)

## 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.