Leveraging vague prior information in general models via iteratively constructed Gamma-minimax estimators

by   Hongxiang Qiu, et al.

Gamma-minimax estimation is an approach to incorporate prior information into an estimation procedure when it is implausible to specify one particular prior distribution. In this approach, we aim for an estimator that minimizes the worst-case Bayes risk over a set Γ of prior distributions. Traditionally, Gamma-minimax estimation is defined for parametric models. In this paper, we define Gamma-minimaxity for general models and propose iterative algorithms with convergence guarantees to compute Gamma-minimax estimators for a general model space and a set of prior distributions constrained by generalized moments. We also propose encoding the space of candidate estimators by neural networks to enable flexible estimation. We illustrate our method in two settings, namely entropy estimation and a problem that arises in biodiversity studies.



page 1

page 2

page 3

page 4


On estimation of nonsmooth functionals of sparse normal means

We study the problem of estimation of the value N_gamma(θ) = sum(i=1)^d ...

Learning Minimax Estimators via Online Learning

We consider the problem of designing minimax estimators for estimating t...

Ensemble minimaxity of James-Stein estimators

This article discusses estimation of a multivariate normal mean based on...

Generalised Entropy MDPs and Minimax Regret

Bayesian methods suffer from the problem of how to specify prior beliefs...

Optimal Rates for Estimation of Two-Dimensional Totally Positive Distributions

We study minimax estimation of two-dimensional totally positive distribu...

Enhanced Balancing of Bias-Variance Tradeoff in Stochastic Estimation: A Minimax Perspective

Biased stochastic estimators, such as finite-differences for noisy gradi...

On the limit behavior of iterated equilibrium distributions for the Gamma and Weibull families

In this paper, we study the evolution of iterated equilibrium distributi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.