# The optimal information complexity of VC learning

arXiv: https://arxiv.org/abs/2610.10600 · HTML: https://mlsanity.com/paper/2610.10600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 1 of its 19 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Builds on (most cited first, 1 of 1)

- [The Optimal Sample Complexity of Multiclass and List Learning](https://mlsanity.com/paper/2604.24749/) (2026)

## Abstract (arXiv)

Steinke and Zakynthinou(2020) introduces the Conditional Mutual Information (CMI) framework of analyzing the information complexity of learning algorithms based on algorithm-dependent information-theoretic quantities. We study one of these quantities, the evaluated Conditional Mutual Information (eCMI). It has been an interesting question whether the optimal PAC guarantee for VC classes can be recovered from the algorithm-dependent analyses via CMI. And we show that it is possible to recover this guarantee by constructing a learning algorithm whose eCMI is of order O(d) in the realizable case, where d is the VC-dimension of the concept class. Specially, our algorithm is a randomized Majority-of-5 base learners with optimal in-expectation generalization guarantee.