Score: 0

Eluder dimension: localise it!

Published: January 14, 2026 | arXiv ID: 2601.09825v1

By: Alireza Bakhtiari , Alex Ayoub , Samuel Robertson and more

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.

Category
Computer Science:
Machine Learning (CS)