Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees

Verónica Álvarez, Santiago Mazuelas, Jose A Lozano
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:486-499, 2022.

Abstract

The statistical characteristics of instance-label pairs often change with time in practical scenarios of supervised classification. Conventional learning techniques adapt to such concept drift accounting for a scalar rate of change by means of a carefully chosen learning rate, forgetting factor, or window size. However, the time changes in common scenarios are multidimensional, i.e., different statistical characteristics often change in a different manner. This paper presents adaptive minimax risk classifiers (AMRCs) that account for multidimensional time changes by means of a multivariate and high-order tracking of the time-varying underlying distribution. In addition, differently from conventional techniques, AMRCs can provide computable tight performance guarantees. Experiments on multiple benchmark datasets show the classification improvement of AMRCs compared to the state-of-the-art and the reliability of the presented performance guarantees.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-alvarez22a, title = {Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees}, author = {{\'A}lvarez, Ver{\'o}nica and Mazuelas, Santiago and Lozano, Jose A}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {486--499}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/alvarez22a/alvarez22a.pdf}, url = {https://proceedings.mlr.press/v162/alvarez22a.html}, abstract = {The statistical characteristics of instance-label pairs often change with time in practical scenarios of supervised classification. Conventional learning techniques adapt to such concept drift accounting for a scalar rate of change by means of a carefully chosen learning rate, forgetting factor, or window size. However, the time changes in common scenarios are multidimensional, i.e., different statistical characteristics often change in a different manner. This paper presents adaptive minimax risk classifiers (AMRCs) that account for multidimensional time changes by means of a multivariate and high-order tracking of the time-varying underlying distribution. In addition, differently from conventional techniques, AMRCs can provide computable tight performance guarantees. Experiments on multiple benchmark datasets show the classification improvement of AMRCs compared to the state-of-the-art and the reliability of the presented performance guarantees.} }
Endnote
%0 Conference Paper %T Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees %A Verónica Álvarez %A Santiago Mazuelas %A Jose A Lozano %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-alvarez22a %I PMLR %P 486--499 %U https://proceedings.mlr.press/v162/alvarez22a.html %V 162 %X The statistical characteristics of instance-label pairs often change with time in practical scenarios of supervised classification. Conventional learning techniques adapt to such concept drift accounting for a scalar rate of change by means of a carefully chosen learning rate, forgetting factor, or window size. However, the time changes in common scenarios are multidimensional, i.e., different statistical characteristics often change in a different manner. This paper presents adaptive minimax risk classifiers (AMRCs) that account for multidimensional time changes by means of a multivariate and high-order tracking of the time-varying underlying distribution. In addition, differently from conventional techniques, AMRCs can provide computable tight performance guarantees. Experiments on multiple benchmark datasets show the classification improvement of AMRCs compared to the state-of-the-art and the reliability of the presented performance guarantees.
APA
Álvarez, V., Mazuelas, S. & Lozano, J.A.. (2022). Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:486-499 Available from https://proceedings.mlr.press/v162/alvarez22a.html.

Related Material