Adaptive Online Estimation of Piecewise Polynomial Trends
Abstract
We consider the framework of non-stationary stochastic optimization [Besbes et al, 2015] with squared error losses and noisy gradient feedback where the dynamic regret of an online learner against a time varying comparator sequence is studied. Motivated from the theory of non-parametric regression, we introduce a new variational constraint that enforces the comparator sequence to belong to a discrete order Total Variation ball of radius . This variational constraint models comparators that have piece-wise polynomial structure which has many relevant practical applications [Tibshirani, 2014]. By establishing connections to the theory of wavelet based non-parametric regression, we design a polynomial time algorithm that achieves the nearly optimal dynamic regret of . The proposed policy is adaptive to the unknown radius . Further, we show that the same policy is minimax optimal for several other non-parametric families of interest.
Keywords
Cite
@article{arxiv.2010.00073,
title = {Adaptive Online Estimation of Piecewise Polynomial Trends},
author = {Dheeraj Baby and Yu-Xiang Wang},
journal= {arXiv preprint arXiv:2010.00073},
year = {2020}
}