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..
Minimax Adaptive Online Nonparametric Regression over Besov spaces
Authors: Paul Liautaud, Pierre Gaillard, Olivier Wintenberger
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study online adversarial regression with convex losses against a rich class of continuous yet highly irregular competitor functions,modeled by Besov spaces Bs pq with general parameters 1 p, q and smoothness s > d p. We introduce an adaptive wavelet-based algorithm that performs sequential prediction without prior knowledge of (s, p, q), and establish minimax-optimal regret bounds against any comparator in Bs pq. We further design a locally adaptive extension capable of sequentially adapting to spatially inhomogeneous smoothness. |
| Researcher Affiliation | Academia | Paul Liautaud Sorbonne Université, CNRS, LPSM F-75005 Paris, France EMAIL Pierre Gaillard Université Grenoble Alpes, Inria CNRS, Grenoble INP, LJK 38000 Grenoble, France EMAIL Olivier Wintenberger Sorbonne Université, CNRS, LPSM F-75005 Paris, France Institut Pauli, CNRS and University of Vienna Oskar-Morgenstern-Platz 1, 1090 Wien, Austria EMAIL |
| Pseudocode | Yes | Algorithm 1: Online Wavelet Decomposition at time t Algorithm 2: Adaptive Online Wavelet Regression |
| Open Source Code | No | Justification: We do not have experimental results on data. |
| Open Datasets | No | Justification: We do not have experimental results on data. |
| Dataset Splits | No | Justification: No experiment. |
| Hardware Specification | No | Justification: No experiment. |
| Software Dependencies | No | Justification: No experiment. |
| Experiment Setup | No | Justification: No experiment. |