Derandomizing Multi-Distribution Learning

Authors: Kasper Green Larsen, Omar Montasser, Nikita Zhivotovskiy

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper is theoretical, and we have no experiments, data or code in the paper.
Researcher Affiliation Academia Kasper Green Larsen Department of Computer Science Aarhus University larsen@cs.au.dk Omar Montasser Department of Statistics and Data Science Yale University omar.montasser@yale.edu Nikita Zhivotovskiy Department of Statistics University of California, Berkeley zhivotovskiy@berkeley.edu
Pseudocode Yes Algorithm 1: DETERMINISTICLEARNER(P, ε, δ, A)
Open Source Code No The paper is theoretical, and we have no experiments, data or code in the paper.
Open Datasets No The paper is theoretical, and we have no experiments, data or code in the paper.
Dataset Splits No The paper is theoretical, and we have no experiments, data or code in the paper.
Hardware Specification No The paper is theoretical, and we have no experiments, data or code in the paper.
Software Dependencies No The paper is theoretical, and we have no experiments, data or code in the paper.
Experiment Setup No The paper is theoretical, and we have no experiments, data or code in the paper.