Computation of Optimal Transport and Related Hedging Problems via Penalization and Neural Networks

This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversarial networks that showcase the generality and effectiveness of the approach.

[1]  Constrained Optimal Transport , 2016, 1610.02940.

[2]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[3]  Nizar Touzi,et al.  A Stochastic Control Approach to No-Arbitrage Bounds Given Marginals, with an Application to Lookback Options , 2013, 1401.3921.

[4]  Roberto Cominetti,et al.  Asymptotic analysis of the exponential penalty trajectory in linear programming , 1994, Math. Program..

[5]  Georg Ch. Pflug,et al.  A Review on Ambiguity in Stochastic Portfolio Optimization , 2018 .

[6]  Christian L'eonard.  A survey of the Schr\"odinger problem and some of its connections with optimal transport , 2013, 1308.0215.

[7]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[8]  Mathias Pohl,et al.  Robust risk aggregation with neural networks , 2018, Mathematical finance.

[9]  Ruodu Wang,et al.  Risk aggregation with dependence uncertainty , 2014 .

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

[11]  J. Teichmann,et al.  Deep hedging , 2018, Quantitative Finance.

[12]  Fei Xia,et al.  Understanding GANs: the LQG Setting , 2017, ArXiv.

[13]  S. S. Vallender.  Calculation of the Wasserstein Distance Between Probability Distributions on the Line , 1974 .

[14]  S. Peng.  G -Expectation, G -Brownian Motion and Related Stochastic Calculus of Itô Type , 2006, math/0601035.

[15]  Aurélien Alfonsi,et al.  Sampling of Probability Measures in the Convex Order and Approximation of Martingale Optimal Transport Problems , 2017 .

[16]  Andreas K. Maier,et al.  Deep Learning for Sampling from Arbitrary Probability Distributions , 2018, MLMIR@MICCAI.

[17]  E Weinan,et al.  Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential Equations , 2017, Communications in Mathematics and Statistics.

[18]  C. Villani.  Optimal Transport: Old and New , 2008 .

[19]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[20]  Gabriel Peyré,et al.  Stochastic Optimization for Large-scale Optimal Transport , 2016, NIPS.

[21]  M. Kupper,et al.  PR ] 2 S ep 2 01 7 Sharpness of improved Fréchet-Hoeffding bounds : an optimal transport approach , 2017 .

[22]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[23]  Patrick Cheridito,et al.  Representation of increasing convex functionals with countably additive measures , 2015, 1502.05763.

[24]  Patrick Cheridito,et al.  Duality Formulas for Robust Pricing and Hedging in Discrete Time , 2016, SIAM J. Financial Math..

[25]  M. Teboulle,et al.  AN OLD‐NEW CONCEPT OF CONVEX RISK MEASURES: THE OPTIMIZED CERTAINTY EQUIVALENT , 2007 .

[26]  Pierre Henry-Labordere,et al.  Automated Option Pricing: Numerical Methods , 2011 .

[27]  Bernard D. Flury.  Acceptance-Rejection Sampling Made Easy , 1990, SIAM Rev..

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Gabriel Peyré,et al.  Iterative Bregman Projections for Regularized Transportation Problems , 2014, SIAM J. Sci. Comput..

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

[31]  Quoc V. Le,et al.  Don't Decay the Learning Rate, Increase the Batch Size , 2017, ICLR.

[32]  V. Strassen.  The Existence of Probability Measures with Given Marginals , 1965 .

[33]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[34]  Gabriel Peyré,et al.  Convergence of Entropic Schemes for Optimal Transport and Gradient Flows , 2015, SIAM J. Math. Anal..

[35]  Duality for increasing convex functionals with countably many marginal constraints , 2015, 1509.08988.

[36]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[37]  Nicolas Courty,et al.  Large Scale Optimal Transport and Mapping Estimation , 2017, ICLR.

[38]  Ludger Rüschendorf,et al.  Computation of sharp bounds on the distribution of a function of dependent risks , 2012, J. Comput. Appl. Math..

[39]  Ludger Rüschendorf,et al.  How robust is the value-at-risk of credit risk portfolios? , 2015 .

[40]  Terry J. Lyons,et al.  Stochastic finance. an introduction in discrete time , 2004 .

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

[42]  Bernhard Schmitzer,et al.  Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems , 2016, SIAM J. Sci. Comput..

[43]  Samuel Drapeau,et al.  Computational aspects of robust optimized certainty equivalents , 2017 .

[44]  L. Kantorovich.  On the Translocation of Masses , 2006 .

[45]  H. Kellerer.  Duality theorems for marginal problems , 1984 .

[46]  P. Embrechts,et al.  Model Uncertainty and VaR Aggregation , 2013 .

[47]  Philippe Artzner,et al.  Coherent Measures of Risk , 1999 .

[48]  A. Papapantoleon,et al.  Improved Fr\'echet--Hoeffding bounds on $d$-copulas and applications in model-free finance , 2016, 1602.08894.