Communication Complexity of Distributed Convex Learning and Optimization

Authors: Yossi Arjevani, Ohad Shamir

NeurIPS 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we take the opposite direction, and study what are the fundamental performance limitations in solving Eq. (1), under several different sets of assumptions. We identify cases where existing algorithms are already optimal (at least in the worst-case), as well as cases where room for further improvement is still possible.
Researcher Affiliation Academia Yossi Arjevani Weizmann Institute of Science Rehovot 7610001, Israel yossi.arjevani@weizmann.ac.il; Ohad Shamir Weizmann Institute of Science Rehovot 7610001, Israel ohad.shamir@weizmann.ac.il
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper is theoretical and focuses on lower bounds; it does not present a new method with associated open-source code.
Open Datasets No The paper is theoretical and focuses on lower bounds for distributed optimization; it does not use or describe any specific datasets for training or experimentation.
Dataset Splits No The paper is theoretical and does not conduct experiments or discuss dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not conduct experiments that would require specific hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any software dependencies or versions for experimental reproduction.
Experiment Setup No The paper is theoretical and focuses on lower bounds, it does not describe an experimental setup, hyperparameters, or training configurations.