Game-Theoretic Algorithms for Conditional Moment Matching

08/19/2022
by   Gokul Swamy, et al.
0

A variety of problems in econometrics and machine learning, including instrumental variable regression and Bellman residual minimization, can be formulated as satisfying a set of conditional moment restrictions (CMR). We derive a general, game-theoretic strategy for satisfying CMR that scales to nonlinear problems, is amenable to gradient-based optimization, and is able to account for finite sample uncertainty. We recover the approaches of Dikkala et al. and Dai et al. as special cases of our general framework before detailing various extensions and how to efficiently solve the game defined by CMR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/24/2011

Minimax Policies for Combinatorial Prediction Games

We address the online linear optimization problem when the actions of th...
research
07/11/2022

Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions

Important problems in causal inference, economics, and, more generally, ...
research
12/26/2020

Are Guessing, Source Coding, and Tasks Partitioning Birds of a Feather?

This paper establishes a close relationship among the four information t...
research
02/21/2020

Kernel Conditional Moment Test via Maximum Moment Restriction

We propose a new family of specification tests called kernel conditional...
research
03/28/2019

Nonlinear Moment Matching for the Simulation-Free Reduction of Structural Systems

This paper transfers the concept of moment matching to nonlinear structu...
research
01/05/2021

Online Multivalid Learning: Means, Moments, and Prediction Intervals

We present a general, efficient technique for providing contextual predi...
research
02/21/2023

A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning

We provide a unifying framework for the design and analysis of multi-cal...

Please sign up or login with your details

Forgot password? Click here to reset