Uncoupled isotonic regression via minimum Wasserstein deconvolution
Authors:
- 2 April 2019
- journal article
- research article
- Published by Oxford University Press (OUP) in Information and Inference: A Journal of the IMA
- Vol. 8 (4) , 691-717
Abstract
Isotonic regression is a standard problem in shape-constrained estimation where the goal is to estimate an unknown non-decreasing regression function $f$ from independent pairs $(x_i, y_i)$ where ${\mathbb{E}}[y_i]=f(x_i), i=1, \ldots n$. While this problem is well understood both statistically and computationally, much less is known about its uncoupled counterpart, where one is given only the unordered sets $\{x_1, \ldots , x_n\}$ 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 $y_i$ and to give an efficient algorithm achieving optimal rates. Both upper and lower bounds employ moment-matching arguments that are also pertinent to learning mixtures of distributions and deconvolution.
Keywords
All Related Versions
Funding Information
- National Science Foundation (DGE-1122374, DMS-1712596, TRIPODS-1740751, IIS-183807)
- Office of Naval Research (N00014-17-1-2147)
- Silicon Valley Community Foundation (2018-182642)
- Massachusetts Institute of Technology
- Josephine De Karman Fellowship Trust
This publication has 27 references indexed in Scilit:
- Deconvolution for the Wasserstein metric and geometric inferenceElectronic Journal of Statistics, 2011
- Risk bounds in isotonic regressionThe Annals of Statistics, 2002
- On nonparametric tests of positivity/monotonicity/convexityThe Annals of Statistics, 2002
- On the degrees of freedom in shape-restricted regressionThe Annals of Statistics, 2000
- Optimal Rate of Convergence for Finite Mixture ModelsThe Annals of Statistics, 1995
- Hellinger-Consistency of Certain Nonparametric Maximum Likelihood EstimatorsThe Annals of Statistics, 1993
- Estimating a Smooth Monotone Regression FunctionThe Annals of Statistics, 1991
- Estimating a Regression FunctionThe Annals of Statistics, 1990
- Estimation of the Correlation Coefficient from a Broken Random SampleThe Annals of Statistics, 1980
- Construction of Sequences Estimating the Mixing DistributionThe Annals of Mathematical Statistics, 1968