English

Eluder dimension: localise it!

Machine Learning 2026-04-21 v2

Abstract

We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds. To address this, we introduce a localisation method for the eluder dimension; our analysis immediately recovers and improves on classic results for Bernoulli bandits, and allows for the first genuine first-order bounds for finite-horizon reinforcement learning tasks with bounded cumulative returns.

Keywords

Cite

@article{arxiv.2601.09825,
  title  = {Eluder dimension: localise it!},
  author = {Alireza Bakhtiari and Alex Ayoub and Samuel Robertson and David Janz and Csaba Szepesvári},
  journal= {arXiv preprint arXiv:2601.09825},
  year   = {2026}
}

Comments

This version corrects a significant error in the published NeurIPS proceedings version. We thank Marc Abeille for bringing the error to our attention

R2 v1 2026-07-01T09:04:53.091Z