A distributional interpretation of robust optimization

By Huan Xu, Constantine Caramanis, Shie Mannor. 2010

67 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Management Science and Operations Research, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Dimitris J. Bertsimas
2. Aurélie C. Thiele
3. Virginie Gabrel
4. Cécile Murat
5. David B. Brown
6. Constantine Caramanis
7. John C. Duchi
8. Hongseok Namkoong

In Management Science and Operations Research

1. Hongseok Namkoong
2. John C. Duchi
3. Aurélie C. Thiele
4. Constantine Caramanis
5. David B. Brown
6. Dimitris J. Bertsimas
7. Virginie Gabrel
8. Aman Sinha

In Statistics and Probability

1. John C. Duchi
2. Hongseok Namkoong
3. Dimitris J. Bertsimas
4. Aurélie C. Thiele
5. Virginie Gabrel
6. Cécile Murat
7. Constantine Caramanis
8. David B. Brown

Citations in the corpus

• Certifying Some Distributional Robustness with Principled Adversarial Training (2017, background): “∈U Unfortunately, this approach is intractable except for specially structured losses, such as the composition of a linear and simple convex function [4, 67, 68].”
• Monte Carlo sampling-based methods for stochastic optimization (2014, unknown): “[241].”
• Certifiable Distributional Robustness with Principled Adversarial Training (2017, background): “Unfortunately, this approach is intractable except for specially structured losses, such as the composition of a linear and simple convex function [3, 51, 52].”
• Recent advances in robust optimization: An overview (2014, background): “Finally, Xu et al. (2012b) study robust principal component analysis in the presence of contaminated data.”
• Distributionally Robust Convex Optimization (2014, unknown): “[61].”
• Theory and Applications of Robust Optimization (2010, background): “(prevalent in many applications, e.g., nance) where samples are the only relevant information a decision maker has on the underlying distribution. Related to distributional uncertainty is the work in [132]. Here, Xu, Caramanis and Mannor show that any robust optimization problem is equivalent to a d”