Solution manifold and Its Statistical Applications

Abstract

A solution manifold is the collection of points in a $d$-dimensional space satisfying a system of $s$ equations with $s<d$. Solution manifolds occur in several statistical problems including hypothesis testing, curved-exponential families, constrained mixture models, partial identifications, and nonparametric set estimation. We analyze solution manifolds both theoretically and algorithmically. In terms of theory, we derive five useful results: the smoothness theorem, the stability theorem (which implies the consistency of a plug-in estimator), the convergence of a gradient flow, the local center manifold theorem and the convergence of the gradient descent algorithm. To numerically approximate a solution manifold, we propose a Monte Carlo gradient descent algorithm. In the case of likelihood inference, we design a manifold constraint maximization procedure to find the maximum likelihood estimator on the manifold. We also develop a method to approximate a posterior distribution defined on a solution manifold.

arXiv commentAccepted to the Electronic Journal of Statistics. 34 page, 6 figures

References in corpus (13)

• Equality of Opportunity in Supervised Learning
• Eulerian Walkers as a model of Self-Organised Criticality
• Chip-Firing and Rotor-Routing on Directed Graphs
• An almost sure invariance principle for random walks in a space-time random environment
• Excited Random Walk
• Sandpile groups and spanning trees of directed line graphs
• Exponential Varieties
• On a general many-dimensional excited random walk
• Limit laws of transient excited random walks on integers
• Interlacements and the Wired Uniform Spanning Forest
• Excited random walks: results, methods, open problems
• Algebraic statistical models
• Excited random walk with periodic cookies

Cited by in corpus (2)

• Rotor walks on transient graphs and the wired spanning forest
• Recurrence of horizontal-vertical walks