Nonparametric Online Regression while Learning the Metric
Lists
Only you see this
Abstract
We study algorithms for online nonparametric regression that learn the directions along which the regression function is smoother. Our algorithm learns the Mahalanobis metric based on the gradient outer product matrix $\boldsymbol{G}$ of the regression function (automatically adapting to the effective rank of this matrix), while simultaneously bounding the regret ---on the same data sequence--- in terms of the spectrum of $\boldsymbol{G}$. As a preliminary step in our analysis, we extend a nonparametric online learning algorithm by Hazan and Megiddo enabling it to compete against functions whose Lipschitzness is measured with respect to an arbitrary Mahalanobis metric.
BibTeX
@inproceedings{kuzborskij2017nonparametric,
author = {Ilja Kuzborskij and Nicolò Cesa-Bianchi},
title = {{Nonparametric Online Regression while Learning the Metric}},
booktitle = {Advances in Neural Information Processing Systems},
year = {2017},
url = {https://openreview.net/forum?id=B1bnPwZ_WB},
}| Fast, smooth and adaptive regression in metric spaces | NeurIPS · 2009 |
| Online nonparametric regression with Sobolev kernels | arXiv · 2021 |
| Online Nonparametric Regression with General Loss Functions | arXiv · 2015 |
| Online Learning with Low Rank Experts | arXiv · 2016 |
| Non-stationary Online Regression | arXiv · 2020 |
| Sequential Nonparametric Regression | ICML · 2012 |