Fast Nonlinear Vector Quantile Regression

05/30/2022
by   Aviv A. Rosenberg, et al.
55

Quantile regression (QR) is a powerful tool for estimating one or more conditional quantiles of a target variable Y given explanatory features X. A limitation of QR is that it is only defined for scalar target variables, due to the formulation of its objective function, and since the notion of quantiles has no standard definition for multivariate distributions. Recently, vector quantile regression (VQR) was proposed as an extension of QR for vector-valued target variables, thanks to a meaningful generalization of the notion of quantiles to multivariate distributions via optimal transport. Despite its elegance, VQR is arguably not applicable in practice due to several limitations: (i) it assumes a linear model for the quantiles of the target Y given the features X; (ii) its exact formulation is intractable even for modestly-sized problems in terms of target dimensions, number of regressed quantile levels, or number of features, and its relaxed dual formulation may violate the monotonicity of the estimated quantiles; (iii) no fast or scalable solvers for VQR currently exist. In this work we fully address these limitations, namely: (i) We extend VQR to the non-linear case, showing substantial improvement over linear VQR; (ii) We propose vector monotone rearrangement, a method which ensures the quantile functions estimated by VQR are monotone functions; (iii) We provide fast, GPU-accelerated solvers for linear and nonlinear VQR which maintain a fixed memory footprint, and demonstrate that they scale to millions of samples and thousands of quantile levels; (iv) We release an optimized python package of our solvers as to widespread the use of VQR in real-world applications.

READ FULL TEXT

page 23

page 27

research
07/03/2023

Vector Quantile Regression on Manifolds

Quantile regression (QR) is a statistical tool for distribution-free est...
research
01/11/2020

A likelihood analysis of quantile-matching transformations

Quantile matching is a strictly monotone transformation that sends the o...
research
12/28/2017

Nonlinear quantile mixed models

In regression applications, the presence of nonlinearity and correlation...
research
04/28/2023

Mixture Quantiles Estimated by Constrained Linear Regression

The paper considers the problem of modeling a univariate random variable...
research
09/07/2017

An Alternative Approach to Functional Linear Partial Quantile Regression

We have previously proposed the partial quantile regression (PQR) predic...
research
07/31/2018

On the Unbiased Asymptotic Normality of Quantile Regression with Fixed Effects

Nonlinear panel data models with fixed individual effects provide an imp...
research
03/17/2022

Lorenz map, inequality ordering and curves based on multidimensional rearrangements

We propose a multivariate extension of the Lorenz curve based on multiva...

Please sign up or login with your details

Forgot password? Click here to reset