Communication Lower Bounds for Distributed Convex Optimization: Partition Data on Features

Authors: Zihao Chen, Luo Luo, Zhihua Zhang

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, with certain restrictions on the communication allowed in the procedures, we develop tight lower bounds on communication rounds for a broad class of non-incremental algorithms under this setting. We also provide a lower bound on communication rounds for a class of (randomized) incremental algorithms. 5 Proof of Main Results In this section, we provide proofs of Theorem 2 and Theorem 4. The proof framework of these theorems are based on (Nesterov 2013).
Researcher Affiliation Academia Zihao Chen Zhiyuan College Shanghai Jiao Tong University z.h.chen@sjtu.edu.cn Luo Luo Department of Computer Science and Engineering Shanghai Jiao Tong University ricky@sjtu.edu.cn Zhihua Zhang School of Mathematical Sciences Peking University zhzhang@math.pku.edu.cn
Pseudocode No The paper defines algorithm families (Fλ,L and Iλ,L) and their operations but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any statements or links indicating that its own source code is publicly available.
Open Datasets No This is a theoretical paper focusing on communication lower bounds for optimization algorithms, not on empirical training with specific datasets. Therefore, it does not provide access information for a dataset.
Dataset Splits No This is a theoretical paper, and it does not describe any experimental setup involving dataset splits for training, validation, or testing.
Hardware Specification No This is a theoretical paper that does not describe running experiments, and therefore, it does not specify any hardware used.
Software Dependencies No This is a theoretical paper focused on mathematical proofs and algorithm analysis, and it does not describe any specific software dependencies with version numbers for experimental reproducibility.
Experiment Setup No This is a theoretical paper that does not describe any specific experimental setup, hyperparameters, or system-level training settings.