Statistics of robust optimization: a generalized empirical likelihood approach
From MaRDI portal
Publication:4958550
Abstract: We study statistical inference and distributionally robust solution methods for stochastic optimization problems, focusing on confidence intervals for optimal values and solutions that achieve exact coverage asymptotically. We develop a generalized empirical likelihood framework---based on distributional uncertainty sets constructed from nonparametric -divergence balls---for Hadamard differentiable functionals, and in particular, stochastic optimization problems. As consequences of this theory, we provide a principled method for choosing the size of distributional uncertainty regions to provide one- and two-sided confidence intervals that achieve exact coverage. We also give an asymptotic expansion for our distributionally robust formulation, showing how robustification regularizes problems by their variance. Finally, we show that optimizers of the distributionally robust formulations we study enjoy (essentially) the same consistency properties as those in classical sample average approximations. Our general approach applies to quickly mixing stationary sequences, including geometrically ergodic Harris recurrent Markov chains.
Recommendations
- The empirical likelihood approach to quantifying uncertainty in sample average approximation
- Recovering best statistical guarantees via the empirical divergence-based distributionally robust optimization
- Distributionally robust optimization under moment uncertainty with application to data-driven problems
- Frameworks and results in distributionally robust optimization
- scientific article; zbMATH DE number 7668294
Cites work
- A framework for optimization under ambiguity
- A note on uniform laws of averages for dependent processes
- Acceleration of Stochastic Approximation by Averaging
- Adaptive subgradient methods for online learning and stochastic optimization
- Ambiguity in portfolio selection
- Asymptotic analysis of stochastic programs
- Asymptotic Behavior of Optimal Solutions in Stochastic Programming
- Asymptotic behavior of statistical estimators and of optimal solutions of stochastic optimization problems
- Asymptotic properties of statistical estimators in stochastic programming
- Asymptotic Statistics
- Asymptotic Theory for Solutions in Statistical Estimation and Stochastic Programming
- Asymptotic Theory of Weakly Dependent Random Processes
- Bartlett-type adjustments for empirical discrepancy test statistics
- Basic properties of strong mixing conditions. A survey and some open questions
- Bounding Stationary Expectations of Markov Processes
- Central limit theorems for empirical and U-processes of stationary mixing sequences
- 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 optimization under moment uncertainty with application to data-driven problems
- Effects of data dimension on empirical likelihood
- Empirical ^-divergence minimizers for Hadamard differentiable functionals
- Empirical likelihood
- Empirical likelihood as a goodness-of-fit measure
- Empirical likelihood in some semiparametric models
- Empirical likelihood is Bartlett-correctable
- Empirical likelihood ratio confidence intervals for a single functional
- Empirical likelihood ratio confidence regions
- Epi‐consistency of convex stochastic programs
- Extending the scope of empirical likelihood
- Generalized Delta Theorems for Multivalued Mappings and Measurable Selections
- Geometric ergodicity and R-positivity for general Markov chains
- High dimensional robust M-estimation: asymptotic variance via approximate message passing
- Higher moment coherent risk measures
- Higher Order Properties of Gmm and Generalized Empirical Likelihood Estimators
- scientific article; zbMATH DE number 439380 (Why is no real title available?)
- scientific article; zbMATH DE number 3911472 (Why is no real title available?)
- scientific article; zbMATH DE number 4060392 (Why is no real title available?)
- scientific article; zbMATH DE number 477581 (Why is no real title available?)
- scientific article; zbMATH DE number 6860839 (Why is no real title available?)
- scientific article; zbMATH DE number 3247810 (Why is no real title available?)
- scientific article; zbMATH DE number 3252891 (Why is no real title available?)
- scientific article; zbMATH DE number 3322635 (Why is no real title available?)
- Introduction to empirical processes and semiparametric inference
- Invariance principles for absolutely regular empirical processes
- Lectures on Stochastic Programming
- Likelihood robust optimization for data-driven problems
- Local Rademacher complexities
- Markov Chains and Stochastic Stability
- Miscellanea. Bartlett adjustment of empirical discrepancy statistics
- Mixing: Properties and examples
- Monte Carlo bounding techniques for determinig solution quality in stochastic programs
- Multivariate Convex Orderings, Dependence, and Stochastic Equality
- On differential stability in stochastic programming
- On the rate of convergence in Wasserstein distance of the empirical measure
- Oracle-based robust optimization via online learning
- Propriétés de mélange des processus autorégressifs polynomiaux. (Mixing properties of polynomial autoregressive processes)
- Quantifying distributional model risk via optimal transport
- Rates of convergence for empirical processes of stationary mixing sequences
- Robust optimization
- Robust sensitivity analysis for stochastic systems
- Robust Stochastic Approximation Approach to Stochastic Programming
- Robust Wasserstein profile inference and applications to machine learning
- Robustness and regularization of support vector machines
- Second-order power comparisons for a class of nonparametric likelihood-based tests
- Some Limit Theorems for Stationary Processes
- Statistical inference for model parameters in stochastic gradient descent
- Stochastic optimization problems with nondifferentiable cost functionals
- Sublinear optimization for machine learning
- Testing Statistical Hypotheses
- The empirical likelihood approach to quantifying uncertainty in sample average approximation
- The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
- Validation analysis of mirror descent stochastic approximation method
- Variance-based regularization with convex objectives
- Variational Analysis
- Weak convergence and empirical processes. With applications to statistics
Cited in
(33)- Data-driven stochastic optimization for distributional ambiguity with integrated confidence region
- Toward theoretical understandings of robust Markov decision processes: sample complexity and asymptotics
- Frameworks and results in distributionally robust optimization
- Partition-based distributionally robust optimization via optimal transport with order cone constraints
- Optimal uncertainty size in distributionally robust inverse covariance estimation
- Calibration of distributionally robust empirical optimization models
- Robust identification of investor beliefs
- Confidence regions of stochastic variational inequalities: error bound approach
- Robust Simulation with Likelihood-Ratio Constrained Input Uncertainty
- Recovering best statistical guarantees via the empirical divergence-based distributionally robust optimization
- Robust Wasserstein profile inference and applications to machine learning
- Variance-based regularization with convex objectives
- Robust Actuarial Risk Analysis
- Bayesian Distributionally Robust Optimization
- Improving fairness generalization through a sample-robust optimization method
- Diametrical risk minimization: theory and computations
- Residuals-based distributionally robust optimization with covariate information
- Higher-order coverage errors of batching methods via Edgeworth expansions on t-statistics
- Auction design with ambiguity: optimality of the first-price auction
- Robust personalized pricing under uncertainty of purchase probabilities
- Prominent roles of conditionally invariant components in domain adaptation: theory and algorithms
- Robust binary and multinomial logit models for classification with data uncertainties
- Distributionally robust optimization and robust statistics
- Distributionally robust optimization
- On regularization schemes for data-driven optimization based on Cressie–Read divergence and CVaR
- Efficient data-driven optimization with noisy data
- Semi-supervised group DRO: combating sparsity with unlabeled data
- The distributionally robust prediction error of the \(\sqrt{\mathrm{LASSO}}\) and related estimators
- Least-squares recovery of dual variables in ROMs for saddle-point problems
- An average-case sensitivity analysis for unmeasured confounding
- Distributionally robust risk evaluation with an isotonic constraint
- Learning and decision-making with data : optimal formulations and phase transitions
- Distributionally robust optimization via regularized robust optimization
This page was built for publication: Statistics of robust optimization: a generalized empirical likelihood approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4958550)
