A New Perspective on Pool-Based Active Classification and False-Discovery Control
Authors: Lalit Jain, Kevin G. Jamieson
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper we provide the first provably sample efficient adaptive algorithm for this problem. Along the way we highlight connections between classification, combinatorial bandits, and FDR control making contributions to each. |
| Researcher Affiliation | Academia | Lalit Jain, Kevin Jamieson {lalitj, jamieson}@cs.washington.edu Paul G. Allen School of Computer Science & Engineering University of Washington, Seattle, WA |
| Pseudocode | Yes | Algorithm 1: Action Elimination for Active Classification; Algorithm 2: Active FDR control in persistent and bounded noise settings. |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described. |
| Open Datasets | No | The paper is theoretical and analyzes algorithms; it does not conduct new experiments requiring its own training data. Figure 1 is a reproduction of data from prior work [33]. |
| Dataset Splits | No | The paper is theoretical and does not present new empirical experiments, thus no dataset splits for validation are discussed. |
| Hardware Specification | No | The paper is theoretical and does not describe any hardware used for experiments. |
| Software Dependencies | No | The paper is theoretical and focuses on algorithms and their analysis, not on their implementation details or specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and defines algorithms and analyzes their properties, not their implementation setup or hyperparameters. |