Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Dynamic Regret Reduces to Kernelized Static Regret
Authors: Andrew Jacobsen, Alessandro Rudi, Francesco Orabona, Nicolò Cesa-Bianchi
NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 41,681 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,506 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We do not include experimental results in this work, as the current focus is on proving the theoretical guarantees and exploring potential applications. |
| Researcher Affiliation | Academia | Andrew Jacobsen Universit a degli Studi di Milano Politecnico di Milano EMAIL Alessandro Rudi Bocconi University EMAIL Francesco Orabona King Abdullah University of Science and Technology (KAUST) Thuwal, 23955-6900, Kingdom of Saudi Arabia EMAIL Nicol o Cesa-Bianchi Universit a degli Studi di Milano Politecnico di Milano EMAIL |
| Pseudocode | Yes | Algorithm 1: Kernelized Online Learning |
| Open Source Code | No | Since this paper does not include experimental results, there is no data or code provided for reproduction. |
| Open Datasets | No | As this paper does not include experimental results, there is no data or code provided for reproduction. |
| Dataset Splits | No | This paper is theoretical and does not contain experimental results, thus no dataset split information is provided. |
| Hardware Specification | No | As the paper does not include experimental results, there is no information provided regarding computational resources. |
| Software Dependencies | No | This paper is theoretical and does not contain experimental results, thus no software dependencies with version numbers are provided. |
| Experiment Setup | No | As this paper does not include experimental results, there are no training or test details provided. |