Online Model Adaptation with Feedforward Compensation

Abulikemu Abuduweili, Changliu Liu
Proceedings of The 7th Conference on Robot Learning, PMLR 229:3687-3709, 2023.

Abstract

To cope with distribution shifts or non-stationarity in system dynamics, online adaptation algorithms have been introduced to update offline-learned prediction models in real-time. Existing online adaptation methods focus on optimizing the prediction model by utilizing feedback from the latest prediction error. Unfortunately, this feedback-based approach is susceptible to forgetting past information. This work proposes an online adaptation method with feedforward compensation, which uses critical data samples from a memory buffer, instead of the latest samples, to optimize the prediction model. We prove that the proposed approach achieves a smaller error bound compared to previously utilized methods in slow time-varying systems. We conducted experiments on several prediction tasks, which clearly illustrate the superiority of the proposed feedforward adaptation method. Furthermore, our feedforward adaptation technique is capable of estimating an uncertainty bound for predictions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-abuduweili23a, title = {Online Model Adaptation with Feedforward Compensation}, author = {Abuduweili, Abulikemu and Liu, Changliu}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {3687--3709}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/abuduweili23a/abuduweili23a.pdf}, url = {https://proceedings.mlr.press/v229/abuduweili23a.html}, abstract = {To cope with distribution shifts or non-stationarity in system dynamics, online adaptation algorithms have been introduced to update offline-learned prediction models in real-time. Existing online adaptation methods focus on optimizing the prediction model by utilizing feedback from the latest prediction error. Unfortunately, this feedback-based approach is susceptible to forgetting past information. This work proposes an online adaptation method with feedforward compensation, which uses critical data samples from a memory buffer, instead of the latest samples, to optimize the prediction model. We prove that the proposed approach achieves a smaller error bound compared to previously utilized methods in slow time-varying systems. We conducted experiments on several prediction tasks, which clearly illustrate the superiority of the proposed feedforward adaptation method. Furthermore, our feedforward adaptation technique is capable of estimating an uncertainty bound for predictions.} }
Endnote
%0 Conference Paper %T Online Model Adaptation with Feedforward Compensation %A Abulikemu Abuduweili %A Changliu Liu %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-abuduweili23a %I PMLR %P 3687--3709 %U https://proceedings.mlr.press/v229/abuduweili23a.html %V 229 %X To cope with distribution shifts or non-stationarity in system dynamics, online adaptation algorithms have been introduced to update offline-learned prediction models in real-time. Existing online adaptation methods focus on optimizing the prediction model by utilizing feedback from the latest prediction error. Unfortunately, this feedback-based approach is susceptible to forgetting past information. This work proposes an online adaptation method with feedforward compensation, which uses critical data samples from a memory buffer, instead of the latest samples, to optimize the prediction model. We prove that the proposed approach achieves a smaller error bound compared to previously utilized methods in slow time-varying systems. We conducted experiments on several prediction tasks, which clearly illustrate the superiority of the proposed feedforward adaptation method. Furthermore, our feedforward adaptation technique is capable of estimating an uncertainty bound for predictions.
APA
Abuduweili, A. & Liu, C.. (2023). Online Model Adaptation with Feedforward Compensation. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:3687-3709 Available from https://proceedings.mlr.press/v229/abuduweili23a.html.

Related Material