Optimal and Efficient Algorithms for Decentralized Online Convex Optimization
Authors: Yuanyu Wan, Tong Wei, Bo Xue, Mingli Song, Lijun Zhang
JMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper focuses on designing and analyzing algorithms for Decentralized Online Convex Optimization (D-OCO). It presents a novel D-OCO algorithm, establishes theoretical regret bounds (e.g., O(nρ 1/4 T)), proves nearly matching lower bounds (e.g., Ω(nρ 1/4 T)), and discusses theoretical guarantees for its projection-free variant. The paper is rich in mathematical derivations, lemmas, and theorems (e.g., "Lemma 1", "Theorem 1", "Proof of Lemma 2"). There are no mentions of empirical studies, dataset evaluations, performance metrics from experiments, or hardware used for running simulations. The work is purely theoretical. |
| Researcher Affiliation | Academia | Yuanyu Wan EMAIL School of Software Technology, Zhejiang University, Ningbo, China State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China Tong Wei EMAIL School of Computer Science and Engineering, Southeast University, Nanjing, China Bo Xue EMAIL Department of Computer Science, City University of Hong Kong, Hong Kong, China Mingli Song EMAIL State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China Lijun Zhang EMAIL National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China School of Artificial Intelligence, Nanjing University, Nanjing, China |
| Pseudocode | Yes | Algorithm 1 AD-FTGL Algorithm 2 CG Algorithm 3 Projection-free Variant of AD-FTGL Algorithm 4 D-FTGL |
| Open Source Code | No | The paper does not contain any explicit statements about the release of source code for the described methodologies, nor does it provide any links to code repositories. |
| Open Datasets | No | This paper is theoretical and focuses on algorithm design and analysis. It does not conduct experiments on datasets, therefore no datasets are mentioned or made available. |
| Dataset Splits | No | This paper is theoretical and does not involve empirical evaluation on datasets. Therefore, there is no mention of dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not describe any experiments that would require specific hardware. No hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and focuses on algorithm design and analysis. It does not mention any specific software dependencies or versions used for implementation or experimentation. |
| Experiment Setup | No | The paper is theoretical and does not include an experimental section or details about system-level training settings or hyperparameters. |