Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Eluder dimension: localise it!
Authors: Alireza Bakhtiari, Alex Ayoub, Samuel Robertson, David Janz, Csaba Szepesvari
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | 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. |
| Researcher Affiliation | Academia | Alireza Bakhtiari University of Alberta EMAIL Alex Ayoub University of Alberta EMAIL Samuel Robertson University of Alberta EMAIL David Janz University of Oxford EMAIL Csaba Szepesvári University of Alberta EMAIL |
| Pseudocode | Yes | Algorithm 1 the ℓ-UCB bandit algorithm Algorithm 2 The ℓ-GOLF algorithm |
| Open Source Code | No | No explicit statement about code availability or links to repositories found in the paper. |
| Open Datasets | No | The paper discusses theoretical frameworks, algorithms (ℓ-UCB, ℓ-GOLF), and regret bounds without conducting empirical studies on specific datasets or providing access information for any datasets. |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments involving datasets, thus no dataset splits are mentioned. |
| Hardware Specification | No | The paper presents theoretical research and does not describe experimental procedures, hence no hardware specifications are provided. |
| Software Dependencies | No | The paper focuses on theoretical algorithms and does not provide specific software dependencies or version numbers for implementation. |
| Experiment Setup | No | The paper is theoretical in nature, focusing on algorithm design and proofs, and therefore does not include details on experimental setup or hyperparameter tuning. |