How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?

Authors: Jun Chen, Hong Chen, Bin Gu

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

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper aims to reveal the impacts by developing a theoretical analysis for two derivative-free algorithms, black-box SCGD and SCSC.
Researcher Affiliation Academia Jun Chen College of Informatics, Huazhong Agricultural University, China cj850487243@163.com Hong Chen College of Informatics, Huazhong Agricultural University, China Engineering Research Center of Intelligent Technology for Agriculture, China chenh@mail.hzau.edu.cn Bin Gu School of Artificial Intelligence, Jilin University, China Mohamed bin Zayed University of Artificial Intelligence jsgubin@gmail.com
Pseudocode Yes Algorithm 1 (Black-box) SCGD / SCSC; Algorithm 2 FOO-based VFL / VFL-CZOFO
Open Source Code No The paper's contributions are from the theoretical analysis perspective. There isn't any data or code.
Open Datasets No The paper's contributions are from the theoretical analysis perspective, and it does not use or provide access to any specific dataset for training.
Dataset Splits No The paper is theoretical and does not describe experimental validation dataset splits.
Hardware Specification No The paper's contributions are from the theoretical analysis perspective, and it does not describe any specific hardware used for running experiments.
Software Dependencies No The paper's contributions are from the theoretical analysis perspective, and it does not describe any specific software dependencies with version numbers for replication.
Experiment Setup No The paper's contributions are from the theoretical analysis perspective, and it does not provide specific experimental setup details like hyperparameters or training configurations.