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..
Prediction with expert advice under additive noise
Authors: Alankrita Bhatt, Victoria Kostina
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper provides fundamental limits on performance, quantified by the regret, in the case when the feedback is corrupted by an additive noise. Our general analysis achieves sharp regret bounds for canonical examples of such additive noise as the Gaussian distribution, the uniform distribution, and a general noise with a log-concave density. This analysis demonstrates how different noise characteristics affect regret bounds and identifies how the regret fundamentally scales as a function of the properties of the noise distribution. Our theoretical guarantees are derived through an analysis combining two complementary techniques: (1) an enhanced exponential weights algorithm adapted for noisy feedback, and (2) information-theoretic lower bounds that precisely characterize what is fundamentally impossible to achieve. |
| Researcher Affiliation | Collaboration | Alankrita Bhatt Granica Computing, Inc. EMAIL Victoria Kostina California Institute of Technology EMAIL |
| Pseudocode | No | The paper describes the 'exponential weights algorithm' and an 'achievability strategy bp EW' but presents them descriptively in paragraph text rather than as structured pseudocode blocks or algorithms with numbered steps in a dedicated section or figure. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing code, nor does it provide any links to repositories for the methodology described. |
| Open Datasets | No | The paper is theoretical and does not use or refer to any specific experimental datasets. It uses abstract problem components such as 'loss vector ℓt' or 'sequence of outcomes ℓn' rather than concrete datasets with access information. |
| Dataset Splits | No | This paper is theoretical and does not conduct experiments involving datasets, therefore, there is no mention of dataset splits for training, testing, or validation. |
| Hardware Specification | No | This paper is theoretical and does not describe any experimental setup or computational results. Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | This paper is theoretical and does not describe any experimental setup or computational results. Therefore, no software dependencies or their specific versions are mentioned. |
| Experiment Setup | No | This paper is theoretical and focuses on mathematical analysis and proofs, without presenting any empirical experiments. Consequently, there are no details regarding experimental setup, such as hyperparameters or training configurations. |