CaltechAUTHORS
  A Caltech Library Service

Competitive Control via Online Optimization with Memory, Delayed Feedback, and Inexact Predictions

Shi, Guanya (2021) Competitive Control via Online Optimization with Memory, Delayed Feedback, and Inexact Predictions. In: 2021 55th Annual Conference on Information Sciences and Systems (CISS). IEEE , Piscataway, NJ, p. 1. ISBN 9781665412681. https://resolver.caltech.edu/CaltechAUTHORS:20210503-115705073

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210503-115705073

Abstract

Recently a line of work has shown the applicability of tools from online optimization for control, leading to online control algorithms with learning-theoretic guarantees, such as sublinear regret. However, the predominant benchmark, static regret, only compares to the best static linear controller in hindsight, which could be arbitrarily sub-optimal compared to the true offline optimal policy in non-stationary environments. Moreover, the common robustness considerations in control theory literature, such as feedback delays and inexact predictions, only have little progress in the context of online learning/optimization guarantees. In this talk, based on our three recent papers, I will present key principles and practical algorithms towards online control with competitive ratio guarantees, which directly bound the suboptimality compared to the true offline optimal policy. First, I will show the deep connections between a novel class of online optimization with memory and online control, which directly translates online optimization guarantees to online control guarantees and gives the first constant-competitive policy with adversarial disturbances [1]. Second, I will analyze the performance of the most popular online policy in the control community, Model Predictive Control (MPC), from the online learning's perspective, and show a few important fundamental limits. Our results give the first finite-time performance guarantees for MPC [3]. Finally, I will discuss the influence of delayed feedback and inexact predictions on competitive ratio analysis [2].


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/ciss50987.2021.9400281DOIArticle
ORCID:
AuthorORCID
Shi, Guanya0000-0002-9075-3705
Additional Information:© 2021 IEEE.
Record Number:CaltechAUTHORS:20210503-115705073
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210503-115705073
Official Citation:G. Shi, "Competitive Control via Online Optimization with Memory, Delayed Feedback, and Inexact Predictions," 2021 55th Annual Conference on Information Sciences and Systems (CISS), 2021, pp. 1-1, doi: 10.1109/CISS50987.2021.9400281
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108940
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:04 May 2021 14:20
Last Modified:04 May 2021 14:20

Repository Staff Only: item control page