Near Minimax Optimal Players for the Finite-Time 3-Expert Prediction Problem
Authors: Yasin Abbasi Yadkori, Peter L. Bartlett, Victor Gabillon
NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The paper primarily focuses on mathematical proofs, lemmas, and theorems concerning minimax strategies and regret rates, such as "We characterize, when K = 3, the regret of the game scaling as 8/(9π)T log(T)2 which gives for the first time the optimal constant in the leading ( T) term of the regret." There are no sections describing empirical experiments, datasets, or performance evaluations. |
| Researcher Affiliation | Collaboration | Authors are affiliated with "Yasin Abbasi-Yadkori Adobe Research Peter L. Bartlett UC Berkeley Victor Gabillon Queensland University of Technology," indicating a mix of industry (Adobe Research) and academic (UC Berkeley, Queensland University of Technology) institutions. |
| Pseudocode | No | The paper does not include any explicitly labeled pseudocode or algorithm blocks. Figure 4 presents mathematical formulas rather than structured algorithmic steps. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating that the source code for the described methodology is provided or publicly available (e.g., |
| Open Datasets | No | The paper is a theoretical work focusing on minimax strategies and regret rates, and does not involve empirical experiments with datasets. Therefore, it does not provide any information about datasets, public availability, or access. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical data or experiments. Consequently, it does not discuss dataset splits, training, validation, or testing partitions. |
| Hardware Specification | No | The paper is purely theoretical and does not conduct or describe any computational experiments. Therefore, it does not provide any hardware specifications for experimental setups. |
| Software Dependencies | No | The paper is purely theoretical and does not conduct or describe any computational experiments. Therefore, it does not provide any specific software dependencies or version numbers. |
| Experiment Setup | No | The paper is purely theoretical and does not describe any empirical experiments or their setup. Therefore, it does not contain specific experimental setup details such as hyperparameter values or training configurations. |