Distributionally Robust Martingale Optimal Transport

We study the problem of bounding path-dependent expectations (within any finite time horizon d) over the class of discrete-time martingales whose marginal distributions lie within a prescribed tolerance of a given collection of benchmark marginal distributions. This problem is a relaxation of the martingale optimal transport (MOT) problem and is motivated by applications to super-hedging in financial markets. We show that the empirical version of our relaxed MOT problem can be approximated within O ( n ) error where n is the number of samples of each of the individual marginal distributions (generated independently) and using a suitably constructed finite-dimensional linear programming problem.

[1]  Mathias Beiglböck,et al.  Model-independent bounds for option prices—a mass transport approach , 2011, Finance Stochastics.

[2]  Martin Klimmek,et al.  Robust price bounds for the forward starting straddle , 2015, Finance Stochastics.

[3]  John C. Duchi,et al.  Learning Models with Uniform Performance via Distributionally Robust Optimization , 2018, ArXiv.

[4]  Karthyek R. A. Murthy,et al.  Quantifying Distributional Model Risk Via Optimal Transport , 2016, Math. Oper. Res..

[5]  G. Pflug,et al.  Multistage Stochastic Optimization , 2014 .

[6]  M. Sion.  On general minimax theorems , 1958 .

[7]  Jan Ob lój.  STATISTICAL ESTIMATION OF SUPERHEDGING PRICES , 2018 .

[8]  Daniel Kuhn,et al.  Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations , 2015, Mathematical Programming.

[9]  Jan Obl'oj,et al.  Dual attainment for the martingale transport problem , 2017, Bernoulli.

[10]  Yinyu Ye,et al.  Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems , 2010, Oper. Res..

[11]  John Duchi,et al.  Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach , 2016, Math. Oper. Res..

[12]  T. Sargent,et al.  Robust Control and Model Uncertainty , 2001 .

[13]  Young-Heon Kim,et al.  Structure of optimal martingale transport plans in general dimensions , 2015, The Annals of Probability.

[14]  Yang Kang,et al.  Distributionally Robust Groupwise Regularization Estimator , 2017, ACML.

[15]  Ian R. Petersen,et al.  Robust Properties of Risk-Sensitive Control , 2000, Math. Control. Signals Syst..

[16]  H. Soner,et al.  Martingale optimal transport and robust hedging in continuous time , 2012, 1208.4922.

[17]  John C. Duchi,et al.  Certifying Some Distributional Robustness with Principled Adversarial Training , 2017, ICLR.

[18]  John C. Duchi,et al.  Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences , 2016, NIPS.

[19]  John C. Duchi,et al.  Variance-based Regularization with Convex Objectives , 2016, NIPS.

[20]  Gaoyue Guo,et al.  Computational methods for martingale optimal transport problems , 2017, The Annals of Applied Probability.

[21]  A. Galichon,et al.  A stochastic control approach to no-arbitrage bounds given marginals, with an application to lookback options , 2014, 1401.3921.

[22]  Tongseok Lim,et al.  Multi-martingale optimal transport , 2016 .

[23]  Mathias Beiglböck,et al.  Optimal transport and Skorokhod embedding , 2013, Inventiones mathematicae.

[24]  D. A. Edwards.  On the existence of probability measures with given marginals , 1978 .

[25]  Marcel Nutz,et al.  Multiperiod martingale transport , 2017 .

[26]  M. KarthyekRajhaaA.,et al.  Robust Wasserstein profile inference and applications to machine learning , 2019, J. Appl. Probab..

[27]  M. Beiglbock,et al.  On a problem of optimal transport under marginal martingale constraints , 2012, 1208.1509.

[28]  Yang Kang,et al.  Sample Out-of-Sample Inference Based on Wasserstein Distance , 2016, Oper. Res..

[29]  Julio Backhoff-Veraguas,et al.  Stability of martingale optimal transport and weak optimal transport , 2019, The Annals of Applied Probability.

[30]  A. Guillin,et al.  On the rate of convergence in Wasserstein distance of the empirical measure , 2013, 1312.2128.

[31]  Nizar Touzi,et al.  Complete Duality for Martingale Optimal Transport on the Line , 2015 .

[32]  Fan Zhang,et al.  Distributionally Robust Local Non-parametric Conditional Estimation , 2020, NeurIPS.

[33]  A. Kleywegt,et al.  Distributionally Robust Stochastic Optimization with Wasserstein Distance , 2016, Math. Oper. Res..

[34]  Gaoyue Guo,et al.  Robust Pricing and Hedging of Options on Multiple Assets and Its Numerics , 2021, SIAM J. Financial Math..