Placeholder, for inference which is robust to a mis=specification of distribution up to some ball in some probaility metric. I saw Jose Blanchet present on Wasserstein distributional robustness at MCM 2019. Bookmarked for later.
To understand: Connections to causal inference, differential privacy, adversarial learning, hedging in portfoliosβ¦
Also to understand: How old is distributional robustness? I feel like when I discovered this literature it was already old, but no-one seems to agree upon a specific foundational publication.
References
Blanchet, Jose, Lin Chen, and Xun Yu Zhou. 2018. βDistributionally Robust Mean-Variance Portfolio Selection with Wasserstein Distances.β arXiv:1802.04885 [Stat], February.
Blanchet, Jose, Yang Kang, and Karthyek Murthy. 2016. βRobust Wasserstein Profile Inference and Applications to Machine Learning.β arXiv:1610.05627 [Math, Stat], October.
Blanchet, Jose, Yang Kang, Fan Zhang, and Karthyek Murthy. 2017. βData-Driven Optimal Cost Selection for Distributionally Robust Optimization.β arXiv:1705.07152 [Stat], May.
Blanchet, Jose, Karthyek Murthy, and Nian Si. 2019. βConfidence Regions in Wasserstein Distributionally Robust Estimation.β arXiv:1906.01614 [Math, Stat], June.
Blanchet, Jose, Karthyek Murthy, and Fan Zhang. 2018. βOptimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes.β arXiv:1810.02403 [Math], October.
Cisneros-Velarde, Pedro, Alexander Petersen, and Sang-Yun Oh. 2020. βDistributionally Robust Formulation and Model Selection for the Graphical Lasso.β In International Conference on Artificial Intelligence and Statistics, 756β65. PMLR.
Diakonikolas, Ilias, Gautam Kamath, Daniel M. Kane, Jerry Li, Ankur Moitra, and Alistair Stewart. 2017. βBeing Robust (in High Dimensions) Can Be Practical.β arXiv:1703.00893 [Cs, Math, Stat], March.
Farokhi, Farhad. 2020. βDistributionally-Robust Machine Learning Using Locally Differentially-Private Data.β arXiv:2006.13488 [Cs, Math, Stat], June.
Gao, Rui, and Anton J. Kleywegt. 2022. βDistributionally Robust Stochastic Optimization with Wasserstein Distance.β arXiv.
Go, Jinwoo, and Tobin Isaac. n.d. βRobust Expected Information Gain for Optimal Bayesian Experimental Design Using Ambiguity Sets,β 10.
Husain, Hisham. 2020. βDistributional Robustness with IPMs and Links to Regularization and GANs.β arXiv:2006.04349 [Cs, Stat], June.
Mahdian, Saied, Jose Blanchet, and Peter Glynn. 2019. βOptimal Transport Relaxations with Application to Wasserstein GANs.β arXiv:1906.03317 [Cs, Math, Stat], June.
Meinshausen, Nicolai. 2018. βCausality from a Distributional Robustness Point of View.β In 2018 IEEE Data Science Workshop (DSW), 6β10.
Mohajerin Esfahani, Peyman, and Daniel Kuhn. 2018. βData-Driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations.β Mathematical Programming 171 (1): 115β66.
Sadeghi, Alireza, Gang Wang, Meng Ma, and Georgios B. Giannakis. 2020. βLearning While Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data.β arXiv:2007.03724 [Cs, Eess, Math], July.
Shapiro, Alexander. 2017. βDistributionally Robust Stochastic Programming.β SIAM Journal on Optimization 27 (4): 2258β75.
Shapiro, Alexander, Enlu Zhou, and Yifan Lin. 2021. βBayesian Distributionally Robust Optimization.β arXiv.
Weichwald, Sebastian, and Jonas Peters. 2020. βCausality in Cognitive Neuroscience: Concepts, Challenges, and Distributional Robustness.β arXiv:2002.06060 [q-Bio, Stat], July.
No comments yet. Why not leave one?