Decentralized Online Convex Optimization in Networked Systems

Authors: Yiheng Lin, Judy Gan, Guannan Qu, Yash Kanoria, Adam Wierman

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that LPC achieves a competitive ratio of 1 + O(ρk T ) + O(ρr S) in an adversarial setting, where ρT and ρS are constants in (0, 1) that increase with the relative strength of temporal and spatial interaction costs, respectively. This is the first competitive ratio bound on decentralized predictive control for networked online convex optimization. Further, we show that the dependence on k and r in our results is near optimal by lower bounding the competitive ratio of any decentralized online algorithm.
Researcher Affiliation Academia 1Department of Computing and Mathematical Sciences, California Institute of Technology 2Decision, Risk, and Operations division, Columbia Business School 3Department of Electrical and Computer Engineering, Carnegie Mellon University.
Pseudocode Yes Algorithm 1 Localized Predictive Control (for agent v)
Open Source Code No The paper does not contain any statement or link regarding the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not report on experiments using a dataset. The multiproduct pricing section is a theoretical example of application, not an empirical evaluation using data.
Dataset Splits No The paper is theoretical and does not report on experiments using dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any computational experiments that would require specific hardware.
Software Dependencies No The paper is theoretical and does not describe the implementation of any software, thus no software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not describe an experimental setup, hyperparameters, or training configurations.