Research
Eluder dimension: localise it!
arXiv:2601.09825v2 Announce Type: replace Abstract: We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot
arXiv:2601.09825v2 Announce Type: replace 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.
Related
- Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets
- A Machine Learning Approach to Two-Stage Adaptive Robust Optimization
- Optimal L2 Regularization in High-dimensional Continual Linear Regression
- On the Theory of Continual Learning with Gradient Descent for Neural Networks
Source: arXiv cs.LG | 2026-04-21