The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.
Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
Open accessAbstract
Many decision problems in science, engineering and economics are affected by uncertain parameters whose distribution is only indirectly observable through samples. The goal of data-driven decision-making is to learn a decision from finitely many training samples that will perform well on unseen test samples. This learning task is difficult even if all training and test samples are drawn from the same distribution -- especially if the dimension of the uncertainty is large relative to the training sample size. Wasserstein distributionally robust optimization seeks data-driven decisions that perform well under the most adverse distribution within a certain Wasserstein distance from a nominal distribution constructed from the training samples. In this tutorial we will argue that this approach has many conceptual and computational benefits. Most prominently, the optimal decisions can often be computed by solving tractable convex optimization problems, and they enjoy rigorous out-of-sample and asymptotic consistency guarantees. We will also show that Wasserstein distributionally robust optimization has interesting ramifications for statistical learning and motivates new approaches for fundamental learning tasks such as classification, regression, maximum likelihood estimation or minimum mean square error estimation, among others.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Boyd, S., & Vandenberghe, L. (2004) · doi:10.1017/cbo9780511804441 · Cited by 56,601
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Advances in Neural Information Processing Systems 29
Teymur, O., Zygalakis, K., & Calderhead, B. (2016) · Cited by 13,881
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
(2012) · Cited by 9,062
Fundamentals of statistical signal processing: Estimation theory
Prasad, K. V. (1994) · Control Engineering Practice · doi:10.1016/0967-0661(94)90195-3 · Cited by 7,902
Hamilton, J. D. (1994) · Princeton University Press eBooks · doi:10.1515/9780691218632 · Cited by 7,293
(2017) · International Conference on Machine Learning · Cited by 6,382
Information Theory, Inference, and Learning Algorithms
(2004) · Kybernetes · doi:10.1108/03684920410534506 · Cited by 4,937
The Earth Mover's Distance as a Metric for Image Retrieval
Rubner, Y., Tomasi, C., & Guibas, L. J. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026543900054 · Cited by 4,568
Parikh, N., & Boyd, S. (2014) · Foundations and Trends® in Optimization · doi:10.1561/2400000003 · Cited by 4,102
Introduction to linear optimization
Bertsimas, D., & Tsitsiklis, J. N. (1997) · Cited by 2,705
Sinkhorn Distances: Lightspeed Computation of Optimal TransportPreprint
Cuturi, M. (2013) · Cited by 2,385
Singh, Y., Janardhanan, S., & Al, S. Y. E. (2010) · Cited by 2,176
Delage, E., & Ye, Y. (2010) · Operations Research · doi:10.1287/opre.1090.0741 · Cited by 1,893
The Markowitz Optimization Enigma: Is ‘Optimized’ Optimal?
Michaud, R. O. (1989) · Financial Analysts Journal · doi:10.2469/faj.v45.n1.31 · Cited by 1,328
Elements of Information Theory
(2013) · Wireless Communications · doi:10.1002/9781118576618.ch7 · Cited by 999
Optimal Transport for Domain Adaptation
Courty, N., Flamary, R., Tuia, D., & Rakotomamonjy, A. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2615921 · Cited by 989
Shapiro, A. (2003) · Handbooks in Operations Research and Management Science · doi:10.1016/s0927-0507(03)10006-0 · Cited by 916
Fast and robust Earth Mover's Distances
Pele, O., & Werman, M. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459199 · Cited by 805
Network Optimization: Continuous and Discrete Models
Bertsekas, D. P. (1998) · Cited by 738
The Fréchet distance between multivariate normal distributions
Dowson, D. C., & Landau, B. V. (1982) · Journal of Multivariate Analysis · doi:10.1016/0047-259x(82)90077-x · Cited by 674
Iterative Bregman Projections for Regularized Transportation Problems
Benamou, J.-D., Carlier, G., Cuturi, M., Nenna, L., & Peyré, G. (2015) · SIAM Journal on Scientific Computing · doi:10.1137/141000439 · Cited by 672
Worst-Case Value-At-Risk and Robust Portfolio Optimization: A Conic Programming Approach
Ghaoui, L. E., Oks, M., & Oustry, F. (2003) · Operations Research · doi:10.1287/opre.51.4.543.16101 · Cited by 662
Distributionally robust joint chance constraints with second-order moment information
Zymler, S., Kühn, D., & Rüstem, B. (2011) · Mathematical Programming · doi:10.1007/s10107-011-0494-7 · Cited by 627
The Analysis of Time Series: An Introduction.
Tong, H., & Chatfield, C. (1981) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2981806 · Cited by 626
A class of Wasserstein metrics for probability distributions.
Givens, C. R., & Shortt, R. M. (1984) · Michigan Mathematical Journal · doi:10.1307/mmj/1029003026 · Cited by 559
Image to Image Translation for Domain Adaptation
Murez, Z., Kolouri, S., Kriegman, D., Ramamoorthi, R., & Kim, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00473 · Cited by 540
On Distributionally Robust Chance-Constrained Linear Programs
Calafiore, G. C., & Ghaoui, L. E. (2006) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-006-9084-x · Cited by 508
Convolutional wasserstein distances: efficient optimal transportation on geometric domains
Solomon, J., de Goes, F., Peyré, G., Cuturi, M., Butscher, A., Nguyen, A., Du, T., & Guibas, L. (2015) · ACM Transactions on Graphics · doi:10.1145/2766963 · Cited by 481
Optimal Mass Transport: Signal processing and machine-learning applications
Kolouri, S., Park, S. R., Thorpe, M., Slepcev, D., & Rohde, G. K. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2695801 · Cited by 443
Auction algorithms for network flow problems: A tutorial introduction
Bertsekas, D. P. (1992) · Computational Optimization and Applications · doi:10.1007/bf00247653 · Cited by 421
Learning Generative Models with Sinkhorn DivergencesPreprint
Genevay, A., Gabriel Peyré, A., & Cuturi, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.00292 · Cited by 395
Scaling algorithms for unbalanced optimal transport problems
Chizat, L., Peyré, G., Schmitzer, B., & Vialard, F.-X. (2018) · Mathematics of Computation · doi:10.1090/mcom/3303 · Cited by 336
The Optimizer’s Curse: Skepticism and Postdecision Surprise in Decision Analysis
Smith, J. E., & Winkler, R. L. (2006) · Management Science · doi:10.1287/mnsc.1050.0451 · Cited by 308
A Linear Time Histogram Metric for Improved SIFT Matching
Pele, O., & Werman, M. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88690-7_37 · Cited by 305
A new algorithm for the assignment problem
Bertsekas, D. P. (1981) · Mathematical Programming · doi:10.1007/bf01584237 · Cited by 292
Monte Carlo sampling-based methods for stochastic optimization
Homem-de-Mello, T., & Bayraksan, G. (2014) · Surveys in Operations Research and Management Science · doi:10.1016/j.sorms.2014.05.001 · Cited by 283
Ambiguity in portfolio selection
Pflug, G., & Wozabal, D. (2007) · Quantitative Finance · doi:10.1080/14697680701455410 · Cited by 261
Multistage Stochastic Optimization
Pflug, G. C., & Pichler, A. (2014) · Springer series in operations research/Springer series in operations research and financial engineering · doi:10.1007/978-3-319-08843-3 · Cited by 258
Deriving robust counterparts of nonlinear uncertain inequalities
Ben-Tal, A., den Hertog, D., & Vial, J.-P. (2015) · Mathematical Programming · doi:10.1007/s10107-014-0750-8 · Cited by 246
Stability of Stochastic Programming Problems
Römisch, W. (2003) · Handbooks in Operations Research and Management Science · doi:10.1016/s0927-0507(03)10008-4 · Cited by 206
Regularized Discrete Optimal Transport
Ferradans, S., Papadakis, N., Peyré, G., & Aujol, J.-F. (2014) · SIAM Journal on Imaging Sciences · doi:10.1137/130929886 · Cited by 188
On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces
Gelbrich, M. (1990) · Mathematische Nachrichten · doi:10.1002/mana.19901470121 · Cited by 175
Distributionally robust multi-item newsvendor problems with multimodal demand distributions
Hanasusanto, G. A., Kuhn, D., Wallace, S. W., & Zymler, S. (2015) · Mathematical Programming · doi:10.1007/s10107-014-0776-y · Cited by 166
Self-citationHanasusanto, G. A., Roitch, V., Kühn, D., & Wiesemann, W. (2015) · Mathematical Programming · doi:10.1007/s10107-015-0896-z · Cited by 154
Wasserstein Dictionary Learning: Optimal Transport-Based Unsupervised Nonlinear Dictionary Learning
Schmitz, M. A., Heitz, M., Bonneel, N., Ngolè, F., Cœurjolly, D., Cuturi, M., Gabriel Peyré, A., & Starck, J. (2018) · SIAM Journal on Imaging Sciences · doi:10.1137/17m1140431 · Cited by 153
Mohajerin Esfahani, P., & Kuhn, D. (2018) · Mathematical Programming · doi:10.1007/s10107-017-1172-1 · Cited by 136
Self-citationTRACTABLE ROBUST EXPECTED UTILITY AND RISK MODELS FOR PORTFOLIO OPTIMIZATION
Natarajan, K., Sim, M., & UICHANCO, J. A. V. (2010) · Mathematical Finance · doi:10.1111/j.1467-9965.2010.00417.x · Cited by 129
Earth mover's distances on discrete surfaces
Solomon, J., Rustamov, R. M., Guibas, L. J., & Butscher, A. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601175 · Cited by 126
Entropic Approximation of Wasserstein Gradient Flows
Gabriel Peyré, A. (2015) · SIAM Journal on Imaging Sciences · doi:10.1137/15m1010087 · Cited by 117
A framework for optimization under ambiguity
Wozabal, D. (2010) · Annals of Operations Research · doi:10.1007/s10479-010-0812-0 · Cited by 112
Sliced Wasserstein Distance for Learning Gaussian Mixture Models
Kolouri, S., Rohde, G. K., & Hoffmann, H. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00361 · Cited by 110
Wasserstein discriminant analysis
Flamary, R., Cuturi, M., Courty, N., & Rakotomamonjy, A. (2018) · Machine Learning · doi:10.1007/s10994-018-5717-1 · Cited by 96
Stability and sensitivity-analysis for stochastic programming
Dupačová, J. (1990) · Annals of Operations Research · doi:10.1007/bf02055193 · Cited by 95
Data-driven inverse optimization with imperfect information
Esfahani, P. M., Shafieezadeh-Abadeh, S., Hanasusanto, G. A., & Kühn, D. (2017) · Mathematical Programming · doi:10.1007/s10107-017-1216-6 · Cited by 94
Self-citationTransport-based single frame super resolution of very low resolution face images
Kolouri, S., & Rohde, G. K. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299121 · Cited by 93
Quadratically Regularized Optimal Transport on Graphs
Essid, M., & Solomon, J. (2018) · SIAM Journal on Scientific Computing · doi:10.1137/17m1132665 · Cited by 84
An Optimal Transportation Approach for Nuclear Structure-Based Pathology
Wang, W., Ozolek, J. A., Slepčev, D., Lee, A. B., Chen, C., & Rohde, G. K. (2010) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2010.2089693 · Cited by 81
Optimal Transport for Diffeomorphic Registration
Feydy, J., Charlier, B., Vialard, F., & Gabriel Peyré, A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66182-7_34 · Cited by 78
A Sparse Multiscale Algorithm for Dense Optimal Transport
Schmitzer, B. (2016) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-016-0653-9 · Cited by 76
Limit laws of the empirical Wasserstein distance: Gaussian distributions
Rippl, T., Munk, A., & Sturm, A. (2016) · Journal of Multivariate Analysis · doi:10.1016/j.jmva.2016.06.005 · Cited by 62
Robust Growth-Optimal Portfolios
Rujeerapaiboon, N., Kühn, D., & Wiesemann, W. (2015) · Management Science · doi:10.1287/mnsc.2015.2228 · Cited by 57
Generalized Sinkhorn Iterations for Regularizing Inverse Problems Using Optimal Mass Transport
Karlsson, J., & Ringh, A. (2017) · SIAM Journal on Imaging Sciences · doi:10.1137/17m111208x · Cited by 57
A Transportation $$L^p$$ Distance for Signal Analysis
Thorpe, M., Park, S., Kolouri, S., et al. (2017) · Journal of Mathematical Imaging and Vision · doi:10.1007/s10851-017-0726-4 · Cited by 54
Wasserstein Loss for Image Synthesis and Restoration
Tartavel, G., Gabriel Peyré, A., & Gousseau, Y. (2016) · SIAM Journal on Imaging Sciences · doi:10.1137/16m1067494 · Cited by 46
Quantum entropic regularization of matrix-valued optimal transport
Gabriel Peyré, A., Chizat, L., Vialard, F., & Solomon, J. (2017) · European Journal of Applied Mathematics · doi:10.1017/s0956792517000274 · Cited by 43
Discovery and visualization of structural biomarkers from MRI using transport-based morphometry
Kundu, S., Kolouri, S., Erickson, K. I., Kramer, A. F., McAuley, E., & Rohde, G. K. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.11.006 · Cited by 30
Extreme points of a ball about a measure with finite support
Owhadi, H., & Scovel, C. (2017) · Communications in Mathematical Sciences · doi:10.4310/cms.2017.v15.n1.a4 · Cited by 8
Cited by
Frameworks and Results in Distributionally Robust Optimization
Rahimian, H., & Mehrotra, S. (2022) · Open Journal of Mathematical Optimization · doi:10.5802/ojmo.15 · Cited by 506
Power systems optimization under uncertainty: A review of methods and applications
Roald, L. A., Pozo, D., Papavasiliou, A., Molzahn, D. K., Kazempour, J., & Conejo, A. (2023) · Electric Power Systems Research · doi:10.1016/j.epsr.2022.108725 · Cited by 317
Device Heterogeneity in Federated Learning: A Superquantile Approach
Laguel, Y., Pillutla, K., Malick, J., & Harchaoui, Z. (2020) · arXiv · doi:10.48550/arxiv.2002.11223 · Cited by 15
Metadata
- Authors
- Kuhn, D., Esfahani, P. M., Nguyen, V. A., & Shafieezadeh-Abadeh, S.
- Venue
- Operations Research & Management Science in the Age of Analytics
- Publisher
- INFORMS
- Published
- 2019-10
- Pages
- 130-166
- OpenAlex
- W2969738732
- Cited by
- 342
- References
- 69
- FWCI
- 56.07
- Type
- book chapter
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.