On the Impossibility of Statistically Improving Empirical Optimization: A Second-Order Stochastic Dominance Perspective

by   Henry Lam, et al.

When the underlying probability distribution in a stochastic optimization is observed only through data, various data-driven formulations have been studied to obtain approximate optimal solutions. We show that no such formulations can, in a sense, theoretically improve the statistical quality of the solution obtained from empirical optimization. We argue this by proving that the first-order behavior of the optimality gap against the oracle best solution, which includes both the bias and variance, for any data-driven solution is second-order stochastically dominated by empirical optimization, as long as suitable smoothness holds with respect to the underlying distribution. We demonstrate this impossibility of improvement in a range of examples including regularized optimization, distributionally robust optimization, parametric optimization and Bayesian generalizations. We also discuss the connections of our results to semiparametric statistical inference and other perspectives in the data-driven optimization literature.



There are no comments yet.


page 1

page 2

page 3

page 4


Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency

This paper considers data-driven chance-constrained stochastic optimizat...

Bounding Optimality Gap in Stochastic Optimization via Bagging: Statistical Efficiency and Stability

We study a statistical method to estimate the optimal value, and the opt...

Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach

We study statistical inference and robust solution methods for stochasti...

Stability and Sample-based Approximations of Composite Stochastic Optimization Problems

Optimization under uncertainty and risk is indispensable in many practic...

Heteroscedasticity-aware residuals-based contextual stochastic optimization

We explore generalizations of some integrated learning and optimization ...

Learning and Decision-Making with Data: Optimal Formulations and Phase Transitions

We study the problem of designing optimal learning and decision-making f...

Learning to reflect: A unifying approach for data-driven stochastic control strategies

Stochastic optimal control problems have a long tradition in applied pro...
This week in AI

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