Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory

Zhiyu Zhang, Ashok Cutkosky, Ioannis Paschalidis
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:8458-8492, 2022.

Abstract

We consider the problem of tracking an adversarial state sequence in a linear dynamical system subject to adversarial disturbances and loss functions, generalizing earlier settings in the literature. To this end, we develop three techniques, each of independent interest. First, we propose a comparator-adaptive algorithm for online linear optimization with movement cost. Without tuning, it nearly matches the performance of the optimally tuned gradient descent in hindsight. Next, considering a related problem called online learning with memory, we construct a novel strongly adaptive algorithm that uses our first contribution as a building block. Finally, we present the first reduction from adversarial tracking control to strongly adaptive online learning with memory. Summarizing these individual techniques, we obtain an adversarial tracking controller with a strong performance guarantee even when the reference trajectory has a large range of movement.

Cite this Paper

BibTeX
@InProceedings{pmlr-v151-zhang22f, title = { Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory }, author = {Zhang, Zhiyu and Cutkosky, Ashok and Paschalidis, Ioannis}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {8458--8492}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/zhang22f/zhang22f.pdf}, url = {https://proceedings.mlr.press/v151/zhang22f.html}, abstract = { We consider the problem of tracking an adversarial state sequence in a linear dynamical system subject to adversarial disturbances and loss functions, generalizing earlier settings in the literature. To this end, we develop three techniques, each of independent interest. First, we propose a comparator-adaptive algorithm for online linear optimization with movement cost. Without tuning, it nearly matches the performance of the optimally tuned gradient descent in hindsight. Next, considering a related problem called online learning with memory, we construct a novel strongly adaptive algorithm that uses our first contribution as a building block. Finally, we present the first reduction from adversarial tracking control to strongly adaptive online learning with memory. Summarizing these individual techniques, we obtain an adversarial tracking controller with a strong performance guarantee even when the reference trajectory has a large range of movement. } }
Endnote
%0 Conference Paper %T Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory %A Zhiyu Zhang %A Ashok Cutkosky %A Ioannis Paschalidis %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-zhang22f %I PMLR %P 8458--8492 %U https://proceedings.mlr.press/v151/zhang22f.html %V 151 %X We consider the problem of tracking an adversarial state sequence in a linear dynamical system subject to adversarial disturbances and loss functions, generalizing earlier settings in the literature. To this end, we develop three techniques, each of independent interest. First, we propose a comparator-adaptive algorithm for online linear optimization with movement cost. Without tuning, it nearly matches the performance of the optimally tuned gradient descent in hindsight. Next, considering a related problem called online learning with memory, we construct a novel strongly adaptive algorithm that uses our first contribution as a building block. Finally, we present the first reduction from adversarial tracking control to strongly adaptive online learning with memory. Summarizing these individual techniques, we obtain an adversarial tracking controller with a strong performance guarantee even when the reference trajectory has a large range of movement.
APA
Zhang, Z., Cutkosky, A. & Paschalidis, I.. (2022). Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:8458-8492 Available from https://proceedings.mlr.press/v151/zhang22f.html.

Related Material