Poster

An Optimal Reduction of TV-Denoising to Adaptive Online Learning

Dheeraj Baby · Xuandong Zhao · Yu-Xiang Wang

Keywords: [ Online Learning ] [ Learning Theory and Statistics ]

[ Abstract ]
Tue 13 Apr 2 p.m. PDT — 4 p.m. PDT

Abstract: We consider the problem of estimating a function from $n$ noisy samples whose discrete Total Variation (TV) is bounded by $C_n$. We reveal a deep connection to the seemingly disparate problem of \emph{Strongly Adaptive} online learning [Daniely et al 2015] and provide an $O(n \log n)$ time algorithm that attains the near minimax optimal rate of $\tilde O (n^{1/3}C_n^{2/3})$ under squared error loss. The resulting algorithm runs online and optimally \emph{adapts} to the \emph{unknown} smoothness parameter $C_n$. This leads to a new and more versatile alternative to wavelets-based methods for (1) adaptively estimating TV bounded functions; (2) online forecasting of TV bounded trends in time series.

Chat is not available.