Incremental Sparsification for Real-time Online Model Learning

Duy Nguyen–Tuong, Jan Peters
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:557-564, 2010.

Abstract

Online model learning in real-time is required by many applications, for example, robot tracking control. It poses a difficult problem, as fast and incremental online regression with large data sets is the essential component and cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for large scale real-time model learning. The proposed approach combines a sparsification method based on an independency measure with a large scale database. In combination with an incremental learning approach such as sequential support vector regression, we obtain a regression method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real robot emphasizes the applicability of the proposed approach in real-time online model learning for real world systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v9-nguyen_tuong10a, title = {Incremental Sparsification for Real-time Online Model Learning}, author = {Nguyen–Tuong, Duy and Peters, Jan}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {557--564}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/nguyen_tuong10a/nguyen_tuong10a.pdf}, url = {https://proceedings.mlr.press/v9/nguyen_tuong10a.html}, abstract = {Online model learning in real-time is required by many applications, for example, robot tracking control. It poses a difficult problem, as fast and incremental online regression with large data sets is the essential component and cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for large scale real-time model learning. The proposed approach combines a sparsification method based on an independency measure with a large scale database. In combination with an incremental learning approach such as sequential support vector regression, we obtain a regression method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real robot emphasizes the applicability of the proposed approach in real-time online model learning for real world systems.} }
Endnote
%0 Conference Paper %T Incremental Sparsification for Real-time Online Model Learning %A Duy Nguyen–Tuong %A Jan Peters %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-nguyen_tuong10a %I PMLR %P 557--564 %U https://proceedings.mlr.press/v9/nguyen_tuong10a.html %V 9 %X Online model learning in real-time is required by many applications, for example, robot tracking control. It poses a difficult problem, as fast and incremental online regression with large data sets is the essential component and cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for large scale real-time model learning. The proposed approach combines a sparsification method based on an independency measure with a large scale database. In combination with an incremental learning approach such as sequential support vector regression, we obtain a regression method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real robot emphasizes the applicability of the proposed approach in real-time online model learning for real world systems.
RIS
TY - CPAPER TI - Incremental Sparsification for Real-time Online Model Learning AU - Duy Nguyen–Tuong AU - Jan Peters BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-nguyen_tuong10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 557 EP - 564 L1 - http://proceedings.mlr.press/v9/nguyen_tuong10a/nguyen_tuong10a.pdf UR - https://proceedings.mlr.press/v9/nguyen_tuong10a.html AB - Online model learning in real-time is required by many applications, for example, robot tracking control. It poses a difficult problem, as fast and incremental online regression with large data sets is the essential component and cannot be realized by straightforward usage of off-the-shelf machine learning methods such as Gaussian process regression or support vector regression. In this paper, we propose a framework for online, incremental sparsification with a fixed budget designed for large scale real-time model learning. The proposed approach combines a sparsification method based on an independency measure with a large scale database. In combination with an incremental learning approach such as sequential support vector regression, we obtain a regression method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques. Implementation on a real robot emphasizes the applicability of the proposed approach in real-time online model learning for real world systems. ER -
APA
Nguyen–Tuong, D. & Peters, J.. (2010). Incremental Sparsification for Real-time Online Model Learning. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:557-564 Available from https://proceedings.mlr.press/v9/nguyen_tuong10a.html.

Related Material