Convergence of Vector Quantization–Based Classifiers to the Bayes Optimal Classifier with Applications to Hybrid System Identification

Aneesh Raghavan, Christos Mavridis, Karl Henrik Johansson, John Baras
Proceedings of The 8th Annual Learning for Dynamics and Control Conference, PMLR 331:472-483, 2026.

Abstract

Vector quantization techniques have been extensively explored as interpretable, data-driven ap- proaches within machine learning, demonstrating significant utility in hybrid system identification. In this study, we establish convergence guarantees for a general framework of quantization-based classifiers, encompassing histogram-based methods, variants of the generalized Lloyd’s algorithm, learning vector quantization, and online deterministic annealing techniques. Utilizing principles from histogram estimation, we analyze the conditions under which these algorithms converge to the Bayes optimal error. These findings provide a rigorous theoretical foundation for the appli- cation of quantization-based algorithms in machine learning tasks associated with cyber-physical systems. An illustrative application in hybrid system identification is also presented.

Cite this Paper

BibTeX
@InProceedings{pmlr-v331-raghavan26a, title = {Convergence of Vector Quantization–Based Classifiers to the Bayes Optimal Classifier with Applications to Hybrid System Identification}, author = {Raghavan, Aneesh and Mavridis, Christos and Johansson, Karl Henrik and Baras, John}, booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference}, pages = {472--483}, year = {2026}, editor = {Sukhatme, Gaurav and Lindemann, Lars and Tu, Stephen and Wierman, Adam and Atanasov, Nikolay}, volume = {331}, series = {Proceedings of Machine Learning Research}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v331/main/assets/raghavan26a/raghavan26a.pdf}, url = {https://proceedings.mlr.press/v331/raghavan26a.html}, abstract = {Vector quantization techniques have been extensively explored as interpretable, data-driven ap- proaches within machine learning, demonstrating significant utility in hybrid system identification. In this study, we establish convergence guarantees for a general framework of quantization-based classifiers, encompassing histogram-based methods, variants of the generalized Lloyd’s algorithm, learning vector quantization, and online deterministic annealing techniques. Utilizing principles from histogram estimation, we analyze the conditions under which these algorithms converge to the Bayes optimal error. These findings provide a rigorous theoretical foundation for the appli- cation of quantization-based algorithms in machine learning tasks associated with cyber-physical systems. An illustrative application in hybrid system identification is also presented.} }
Endnote
%0 Conference Paper %T Convergence of Vector Quantization–Based Classifiers to the Bayes Optimal Classifier with Applications to Hybrid System Identification %A Aneesh Raghavan %A Christos Mavridis %A Karl Henrik Johansson %A John Baras %B Proceedings of The 8th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2026 %E Gaurav Sukhatme %E Lars Lindemann %E Stephen Tu %E Adam Wierman %E Nikolay Atanasov %F pmlr-v331-raghavan26a %I PMLR %P 472--483 %U https://proceedings.mlr.press/v331/raghavan26a.html %V 331 %X Vector quantization techniques have been extensively explored as interpretable, data-driven ap- proaches within machine learning, demonstrating significant utility in hybrid system identification. In this study, we establish convergence guarantees for a general framework of quantization-based classifiers, encompassing histogram-based methods, variants of the generalized Lloyd’s algorithm, learning vector quantization, and online deterministic annealing techniques. Utilizing principles from histogram estimation, we analyze the conditions under which these algorithms converge to the Bayes optimal error. These findings provide a rigorous theoretical foundation for the appli- cation of quantization-based algorithms in machine learning tasks associated with cyber-physical systems. An illustrative application in hybrid system identification is also presented.
APA
Raghavan, A., Mavridis, C., Johansson, K.H. & Baras, J.. (2026). Convergence of Vector Quantization–Based Classifiers to the Bayes Optimal Classifier with Applications to Hybrid System Identification. Proceedings of The 8th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 331:472-483 Available from https://proceedings.mlr.press/v331/raghavan26a.html.

Related Material