A Bayesian risk approach to data-driven stochastic optimization: formulations and asymptotics
From MaRDI portal
Abstract: A large class of stochastic programs involve optimizing an expectation taken with respect to an underlying distribution that is unknown in practice. One popular approach to addressing the distributional uncertainty, known as the distributionally robust optimization (DRO), is to hedge against the worst case over an uncertainty set of candidate distributions. However, it has been observed that inappropriate construction of the uncertainty set can sometimes result in over-conservative solutions. To explore the middle ground between optimistically ignoring the distributional uncertainty and pessimistically fixating on the worst-case scenario, we propose a Bayesian risk optimization (BRO) framework for parametric underlying distributions, which is to optimize a risk functional applied to the posterior distribution of an unknown distribution parameter. Of our particular interest are four risk functionals: mean, mean-variance, value-at-risk, and conditional value-at-risk. To unravel the implication of BRO, we establish the consistency of objective functions and optimal solutions, as well as the asymptotic normality of objective functions and optimal values. More importantly, our analysis reveals a hidden interpretation: the objectives of BRO can be approximately viewed as a weighted sum of posterior mean objective and the (squared) half-width of the true objective's confidence interval.
Recommendations
Cites work
- scientific article; zbMATH DE number 1667417 (Why is no real title available?)
- scientific article; zbMATH DE number 3130649 (Why is no real title available?)
- scientific article; zbMATH DE number 1354815 (Why is no real title available?)
- scientific article; zbMATH DE number 977420 (Why is no real title available?)
- scientific article; zbMATH DE number 1534302 (Why is no real title available?)
- scientific article; zbMATH DE number 3238721 (Why is no real title available?)
- scientific article; zbMATH DE number 3257962 (Why is no real title available?)
- scientific article; zbMATH DE number 3063387 (Why is no real title available?)
- A Bernstein-von Mises theorem for smooth functionals in semiparametric models
- A Bernstein-von Mises theorem in the nonparametric right-censoring model
- Asymptotic Statistics
- Asymptotic analysis of stochastic programs
- Bernstein-von Mises theorem for linear functionals of the density
- Coherent measures of risk
- Data-driven chance constrained stochastic program
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- Data-driven robust optimization
- Distributionally Robust Convex Optimization
- Distributionally robust joint chance constraints with second-order moment information
- Distributionally robust optimization under moment uncertainty with application to data-driven problems
- Distributionally robust stochastic programming
- Lectures on stochastic programming. Modeling and theory.
- Likelihood robust optimization for data-driven problems
- On Bayes procedures
- Overlapping batches for the assessment of solution quality in stochastic programs
- Probability. Theory and examples.
- Rates of convergence of posterior distributions.
- Real analysis
- Robust Mean-Covariance Solutions for Stochastic Optimization
- Robust convex optimization
- Robust empirical optimization is almost the same as mean-variance optimization
- Robust sensitivity analysis for stochastic systems
- Simulation optimization of risk measures with adaptive risk levels
- Statistical estimation of composite risk functionals and risk optimization problems
- Stochastic finance. An introduction in discrete time
- The asymptotic equivalence of Bayes and maximum likelihood estimation
- The sample average approximation method for stochastic discrete optimization
Cited in
(9)- On regularization schemes for data-driven optimization based on Cressie–Read divergence and CVaR
- Risk-adaptive approaches to stochastic optimization: a survey
- Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency
- A Bayesian approach to data-driven multi-stage stochastic optimization
- Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data
- Calibration of distributionally robust empirical optimization models
- Distributionally robust optimization with generalized total variation ambiguity sets
- Bayesian Distributionally Robust Optimization
- Data-driven stochastic optimization for distributional ambiguity with integrated confidence region
This page was built for publication: A Bayesian risk approach to data-driven stochastic optimization: formulations and asymptotics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4641673)
