Simple and near-optimal algorithms for hidden stratification and multi-group learning

Authors: Christopher J Tosh, Daniel Hsu

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem. All proofs are presented in the appendix.
Researcher Affiliation Collaboration 1Memorial Sloan Kettering Cancer Center, New York, NY 2Department of Computer Science, Columbia University, New York, NY.
Pseudocode Yes Algorithm 1 PREPEND, Algorithm 2 Reduction to sleeping experts, Algorithm 3 Consistent majority algorithm, Algorithm 4 MLC-HEDGE in the multi-group setting.
Open Source Code No The paper does not provide any statement about releasing source code for the described methodology or links to a code repository.
Open Datasets No The paper is theoretical and discusses 'n i.i.d. training examples drawn from a distribution D' but does not specify or provide access information for any public dataset.
Dataset Splits No The paper is theoretical and does not discuss specific dataset splits (training, validation, test) needed for reproducibility.
Hardware Specification No The paper focuses on theoretical algorithms and proofs, and therefore does not mention any hardware specifications used for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies with version numbers.
Experiment Setup No The paper describes algorithms theoretically but does not provide specific experimental setup details like hyperparameter values or training configurations.