Universally Consistent Online Learning with Arbitrarily Dependent Responses

Steve Hanneke
Proceedings of The 33rd International Conference on Algorithmic Learning Theory, PMLR 167:488-497, 2022.

Abstract

This work provides an online learning rule that is universally consistent under processes on (X,Y) pairs, under conditions only on the X process. As a special case, the conditions admit all processes on (X,Y) such that the process on X is stationary. This generalizes past results which required stationarity for the joint process on (X,Y), and additionally required this process to be ergodic. In particular, this means that ergodicity is superfluous for the purpose of universally consistent online learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v167-hanneke22a, title = {Universally Consistent Online Learning with Arbitrarily Dependent Responses}, author = {Hanneke, Steve}, booktitle = {Proceedings of The 33rd International Conference on Algorithmic Learning Theory}, pages = {488--497}, year = {2022}, editor = {Dasgupta, Sanjoy and Haghtalab, Nika}, volume = {167}, series = {Proceedings of Machine Learning Research}, month = {29 Mar--01 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v167/hanneke22a/hanneke22a.pdf}, url = {https://proceedings.mlr.press/v167/hanneke22a.html}, abstract = {This work provides an online learning rule that is universally consistent under processes on (X,Y) pairs, under conditions only on the X process. As a special case, the conditions admit all processes on (X,Y) such that the process on X is stationary. This generalizes past results which required stationarity for the joint process on (X,Y), and additionally required this process to be ergodic. In particular, this means that ergodicity is superfluous for the purpose of universally consistent online learning.} }
Endnote
%0 Conference Paper %T Universally Consistent Online Learning with Arbitrarily Dependent Responses %A Steve Hanneke %B Proceedings of The 33rd International Conference on Algorithmic Learning Theory %C Proceedings of Machine Learning Research %D 2022 %E Sanjoy Dasgupta %E Nika Haghtalab %F pmlr-v167-hanneke22a %I PMLR %P 488--497 %U https://proceedings.mlr.press/v167/hanneke22a.html %V 167 %X This work provides an online learning rule that is universally consistent under processes on (X,Y) pairs, under conditions only on the X process. As a special case, the conditions admit all processes on (X,Y) such that the process on X is stationary. This generalizes past results which required stationarity for the joint process on (X,Y), and additionally required this process to be ergodic. In particular, this means that ergodicity is superfluous for the purpose of universally consistent online learning.
APA
Hanneke, S.. (2022). Universally Consistent Online Learning with Arbitrarily Dependent Responses. Proceedings of The 33rd International Conference on Algorithmic Learning Theory, in Proceedings of Machine Learning Research 167:488-497 Available from https://proceedings.mlr.press/v167/hanneke22a.html.

Related Material