A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
Authors: Tor Lattimore
NeurIPS 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The main contribution is the new assumption, algorithm, and the proof of Theorem 2 (see 2). The upper bound is also complemented by an asymptotic lower bound ( 3) that applies to all strategies with sub-polynomial regret and all bandit problems with bounded kurtosis. |
| Researcher Affiliation | Industry | Tor Lattimore EMAIL Now at Deep Mind, London. |
| Pseudocode | No | The paper describes an algorithm in prose within Section 2, but it is not presented in a structured pseudocode block or a clearly labeled algorithm figure. |
| Open Source Code | No | The paper does not provide any concrete access to source code (e.g., a specific repository link, an explicit code release statement, or mention of code in supplementary materials) for the methodology described. |
| Open Datasets | No | This is a theoretical paper focusing on mathematical derivations and algorithm design. It does not conduct empirical studies with datasets; hence, there is no mention of publicly available datasets for training or other purposes. |
| Dataset Splits | No | This is a theoretical paper and does not describe empirical experiments. Therefore, there are no specific dataset split details (e.g., train/validation/test percentages or counts) provided. |
| Hardware Specification | No | This is a theoretical paper. It does not describe any experimental setup that would require hardware, and thus no hardware specifications are provided. |
| Software Dependencies | No | This is a theoretical paper focusing on mathematical and algorithmic contributions. It does not describe any experimental setup that would require specific software dependencies or their versions. |
| Experiment Setup | No | This is a theoretical paper. It does not describe any empirical experimental setup, and therefore no specific hyperparameters, training configurations, or system-level settings are provided. |