Uncoupled isotonic regression via minimum Wasserstein deconvolution

Presented by:
Philippe Rigollet
Date:
Monday 25th June 2018 - 11:45 to 12:30
Venue:
INI Seminar Room 1
Abstract:
Isotonic regression is a standard problem in shape constrained estimation where the goal is to estimate an unknown nondecreasing regression function $f$ from independent pairs $(x_i,y_i)$ where $\E[y_i]=f(x_i), i=1, \ldots n$. While this problem is well understood both statistically and computationally, much less is known about its uncoupled counterpart where one is given uncoupled $\{x_1, \ldots, x_n\}$ and $\{y_1, \ldots, y_n\}$. In this work, we leverage tools from optimal transport theory to derive minimax rates under weak moments conditions on $y_i$ together with an efficient algorithm. Both upper and lower bounds are articulated around moment-matching arguments that are also pertinent to learning mixtures of distributions and deconvolution. [Joint work with Jonathan Weed (MIT)]
The video for this talk should appear here if JavaScript is enabled.
If it doesn't, something may have gone wrong with our embedded player.
We'll get it fixed as soon as possible.