Optimality and Stability in Federated Learning: A Game-theoretic Approach

Authors: Kate Donahue, Jon Kleinberg

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The results in this paper are theoretical and do not depend on any experiments or code.
Researcher Affiliation Academia Kate Donahue Department of Computer Science Cornell University kdonahue@cs.cornell.edu Jon Kleinberg Departments of Computer Science and Information Science Cornell University kleinber@cs.cornell.edu
Pseudocode No The paper describes an algorithm in text (Theorem 1 and its explanation) but does not present it in a structured pseudocode or algorithm block format.
Open Source Code Yes The results in this paper are theoretical and do not depend on any experiments or code. However, while writing the paper, we found it useful to write and work with code to check conjectures. Some of that code is publicly available at github.com/kpdonahue/model_sharing_games.
Open Datasets No The results in this paper are theoretical and do not depend on any experiments or code, thus no datasets are used for training.
Dataset Splits No The results in this paper are theoretical and do not depend on any experiments or code, thus no dataset splits for validation are provided.
Hardware Specification No The results in this paper are theoretical and do not depend on any experiments or code, thus no hardware specifications for running experiments are mentioned.
Software Dependencies No The paper is theoretical and does not rely on specific software dependencies with version numbers for its core findings.
Experiment Setup No The paper is theoretical and does not describe any experimental setup with hyperparameters or system-level training settings.