A distributional interpretation of robust optimization
From MaRDI portal
Abstract: Lasso, or regularized least squares, has been explored extensively for its remarkable sparsity properties. It is shown in this paper that the solution to Lasso, in addition to its sparsity, has robustness properties: it is the solution to a robust optimization problem. This has two important consequences. First, robustness provides a connection of the regularizer to a physical property, namely, protection from noise. This allows a principled selection of the regularizer, and in particular, generalizations of Lasso that also yield convex optimization problems are obtained by considering different uncertainty sets. Secondly, robustness can itself be used as an avenue to exploring different properties of the solution. In particular, it is shown that robustness of the solution explains why the solution is sparse. The analysis as well as the specific results obtained differ from standard sparsity results, providing different geometric intuition. Furthermore, it is shown that the robust optimization formulation is related to kernel density estimation, and based on this approach, a proof that Lasso is consistent is given using robustness directly. Finally, a theorem saying that sparsity and algorithmic stability contradict each other, and hence Lasso is not stable, is presented.
Recommendations
- Distributionally Robust Convex Optimization
- Distributionally robust optimization under moment uncertainty with application to data-driven problems
- Data-driven robust optimization
- Frameworks and results in distributionally robust optimization
- Distributionally robust optimization. A review on theory and applications
Cited in
(33)- scientific article; zbMATH DE number 5618680 (Why is no real title available?)
- Distributionally robust optimization for engineering design under uncertainty
- Distributionally robust optimization
- An Approximation Scheme for Distributionally Robust Nonlinear Optimization
- Decomposition algorithm for distributionally robust optimization using Wasserstein metric with an application to a class of regression models
- On the polynomial solvability of distributionally robust k-sum optimization
- The Value of Randomized Solutions in Mixed-Integer Distributionally Robust Optimization Problems
- Distributionally Robust Linear and Discrete Optimization with Marginals
- Distributionally robust optimization with polynomial densities: theory, models and algorithms
- Residuals-based distributionally robust optimization with covariate information
- Robust defibrillator deployment under cardiac arrest location uncertainty via row-and-column generation
- Distributionally Robust Convex Optimization
- Recent advances in robust optimization: an overview
- A modified exchange algorithm for distributional robust optimization and applications in risk management
- Robust domain adaptation
- Convergence analysis for distributionally robust optimization and equilibrium problems
- Practicable robust stochastic optimization under divergence measures with an application to equitable humanitarian response planning
- A distributionally robust area under curve maximization model
- Calibration of distributionally robust empirical optimization models
- Dynamic optimization with side information
- Inseparable robust reward-risk optimization models with distribution uncertainty
- Likelihood robust optimization for data-driven problems
- Feature uncertainty bounds for explicit feature maps and large robust nonlinear SVM classifiers
- Stability and continuity in robust optimization
- scientific article; zbMATH DE number 1457529 (Why is no real title available?)
- Distributionally robust optimization. A review on theory and applications
- On data-driven computation of information transfer for causal inference in discrete-time dynamical systems
- Technical note -- two-stage sample robust optimization
- Mean robust optimization
- A Lagrangian dual method for two-stage robust optimization with binary uncertainties
- A survey of nonlinear robust optimization
- Distributionally robust expectation inequalities for structured distributions
- A unified framework for stochastic optimization
This page was built for publication: A distributional interpretation of robust optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2884306)
