Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms

Authors: Ming Yang, Xiyuan Wei, Tianbao Yang, Yiming Ying

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we provide the stability and generalization analysis of stochastic compositional gradient descent algorithms in the framework of statistical learning theory.
Researcher Affiliation Academia 1Department of Mathematics and Statistics, State University of New York at Albany, Albany, NY 12222, USA 2Department of Computer Science and Engineering, Texas A&M University, College Station, TX 77843, USA 3The University of Sydney, School of Mathematics and Statistics, Sydney, NSW 2006, Australia.
Pseudocode Yes Algorithm 1 (Stochastically Corrected) Stochastic Compositional Gradient Descent
Open Source Code No The paper does not provide any statement about making its source code publicly available or provide a link to a code repository.
Open Datasets No The paper is theoretical and focuses on analysis rather than experimental evaluation, so it does not describe using specific publicly available datasets for training.
Dataset Splits No The paper is theoretical and does not describe experimental setup details such as training, validation, or test data splits.
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for experiments.
Software Dependencies No The paper is theoretical and does not describe specific software dependencies or version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not provide specific experimental setup details such as hyperparameters or training configurations.