Concentration of risk measures: A Wasserstein distance approach
Authors: Sanjay P. Bhat, Prashanth L.A.
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our goal is to derive concentration bounds for estimators of all three risk measures, and we achieve this in a novel manner by relating the estimation error to the Wasserstein distance between the empirical and true distributions, and then using known concentration bounds for the latter. and The result below bounds the regret of CVa R-LCB algorithm, and the proof is a straightforward adaptation of that used to establish the regret bound of the regular UCB algorithm in [Auer et al., 2002]. |
| Researcher Affiliation | Collaboration | Sanjay P. Bhat Tata Consultancy Services Limited Hyderabad, Telangana, India sanjay.bhat@tcs.com and Prashanth L.A. Department of Computer Science and Engineering Indian Institute of Technology Madras, India prashla@cse.iitm.ac.in |
| Pseudocode | No | The CVa R-LCB algorithm is described in the text, but it is not presented as a formal pseudocode block or clearly labeled algorithm. |
| Open Source Code | No | There is no explicit statement or link in the paper indicating that source code for the described methodology is provided or made publicly available. |
| Open Datasets | No | The paper is theoretical and focuses on deriving concentration bounds for estimators based on i.i.d. samples, rather than using specific publicly available datasets for training. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical validation or dataset splits. |
| Hardware Specification | No | No specific hardware details are mentioned for running experiments, as the paper is theoretical. |
| Software Dependencies | No | No specific software dependencies with version numbers are mentioned. |
| Experiment Setup | No | The paper is theoretical and does not include details on experimental setup or hyperparameters for empirical evaluation. |