Doubly Robust Off-Policy Learning on Low-Dimensional Manifolds by Deep Neural Networks

11/03/2020
by   Minshuo Chen, et al.
0

Causal inference explores the causation between actions and the consequent rewards on a covariate set. Recently deep learning has achieved a remarkable performance in causal inference, but existing statistical theories cannot well explain such an empirical success, especially when the covariates are high-dimensional. Most theoretical results in causal inference are asymptotic, suffer from the curse of dimensionality, and only work for the finite-action scenario. To bridge such a gap between theory and practice, this paper studies doubly robust off-policy learning by deep neural networks. When the covariates lie on a low-dimensional manifold, we prove nonasymptotic regret bounds, which converge at a fast rate depending on the intrinsic dimension of the manifold. Our results cover both the finite- and continuous-action scenarios. Our theory shows that deep neural networks are adaptive to the low-dimensional geometric structures of the covariates, and partially explains the success of deep learning for causal inference.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/07/2021

Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks

Most of existing statistical theories on deep neural networks have sampl...
research
10/10/2022

DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning

Causal mediation analysis can unpack the black box of causality and is t...
research
06/26/2023

Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories

Existing theories on deep nonparametric regression have shown that when ...
research
04/24/2020

A Causal Modeling Framework with Stochastic Confounders

This work aims to extend the current causal inference framework to incor...
research
07/04/2023

Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks

Convolutional residual neural networks (ConvResNets), though overparamet...
research
05/02/2023

The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold

We develop information-geometric techniques to analyze the trajectories ...
research
01/01/2022

Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces

Learning operators between infinitely dimensional spaces is an important...

Please sign up or login with your details

Forgot password? Click here to reset