Hardness results for Multimarginal Optimal Transport problems

Multimarginal Optimal Transport (MOT) is the problem of linear programming over joint probability distributions with fixed marginals. A key issue in many applications is the complexity of solving MOT: the linear program has exponential size in the number of marginals k and their support sizes n. A recent line of work has shown that MOT is poly(n,k)-time solvable for certain families of costs that have poly(n,k)-size implicit representations. However, it is unclear what further families of costs this line of algorithmic research can encompass. In order to understand these fundamental limitations, this paper initiates the study of intractability results for MOT. Our main technical contribution is developing a toolkit for proving NP-hardness and inapproximability results for MOT problems. We demonstrate this toolkit by using it to establish the intractability of a number of MOT problems studied in the literature that have resisted previous algorithmic efforts. For instance, we provide evidence that repulsive costs make MOT intractable by showing that several such problems of interest are NP-hard to solve--even approximately.

[1]  V. A. Yemelicher,et al.  Polytopes, Graphs and Optimisation , 1984 .

[2]  Michael I. Jordan,et al.  Variational inference in graphical models: The view from the marginal polytope , 2008 .

[3]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[4]  Francis R. Bach,et al.  Learning with Submodular Functions: A Convex Optimization Perspective , 2011, Found. Trends Mach. Learn..

[5]  Stefanie Jegelka,et al.  Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets , 2014, NIPS.

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

[7]  Codina Cotar,et al.  Density Functional Theory and Optimal Transportation with Coulomb Cost , 2011, 1104.0603.

[8]  Andrew R. Teel,et al.  ESAIM: Control, Optimisation and Calculus of Variations , 2022 .

[9]  Hariharan Narayanan,et al.  Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions , 2015, COLT.

[10]  Satoru Fujishige,et al.  Submodular functions and optimization , 1991 .

[11]  Simone Di Marino,et al.  An entropy minimization approach to second-order variational mean-field games , 2018, Mathematical Models and Methods in Applied Sciences.

[12]  Friedrich Eisenbrand,et al.  On largest volume simplices and sub-determinants , 2014, SODA.

[13]  Leonard Pitt,et al.  A bounded approximation for the minimum cost 2-sat problem , 1992, Algorithmica.

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

[15]  G. Buttazzo,et al.  Optimal-transport formulation of electronic density-functional theory , 2012, 1205.4514.

[16]  L. Lovász,et al.  Geometric Algorithms and Combinatorial Optimization , 1981 .

[17]  Brendan Pass.  Multi-marginal optimal transport: theory and applications , 2014, 1406.0026.

[18]  G. Carlier,et al.  A Numerical Method to Solve Multi-Marginal Optimal Transport Problems with Coulomb Cost , 2016 .

[19]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[20]  Steffen Borgwardt,et al.  Discrete Wasserstein barycenters: optimal transport for discrete data , 2015, Mathematical Methods of Operations Research.

[21]  Yuanzhi Li,et al.  Algorithms and matching lower bounds for approximately-convex optimization , 2016, NIPS.

[22]  Michael I. Jordan,et al.  On the Complexity of Approximating Multimarginal Optimal Transport , 2019, ArXiv.

[23]  Simone Di Marino,et al.  Optimal transportation theory with repulsive costs , 2015, 1506.04565.

[24]  Martin Grötschel,et al.  The ellipsoid method and its consequences in combinatorial optimization , 1981, Comb..

[25]  Pavel Dvurechensky,et al.  Multimarginal Optimal Transport by Accelerated Alternating Minimization , 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

[26]  Adam M. Oberman,et al.  NUMERICAL METHODS FOR MATCHING FOR TEAMS AND WASSERSTEIN BARYCENTERS , 2014, 1411.3602.

[27]  Johan Karlsson,et al.  Multi-marginal Optimal Transport and Schr\"odinger Bridges on Trees , 2020, 2004.06909.

[28]  S. Friedland.  Tensor optimal transport, distance between sets of measures and tensor scaling , 2020, ArXiv.

[29]  Rahul Singh,et al.  Multi-Marginal Optimal Transport and Probabilistic Graphical Models , 2020, IEEE Transactions on Information Theory.

[30]  Richard M. Karp,et al.  Reducibility Among Combinatorial Problems , 1972, 50 Years of Integer Programming.

[31]  Jean-David Benamou,et al.  Generalized incompressible flows, multi-marginal transport and Sinkhorn algorithm , 2017, Numerische Mathematik.

[32]  Steffen Borgwardt,et al.  On the computational complexity of finding a sparse Wasserstein barycenter , 2019, Journal of Combinatorial Optimization.

[33]  Edward D. Kim,et al.  Combinatorics and geometry of transportation polytopes: An update , 2013, Discrete Geometry and Algebraic Combinatorics.

[34]  U. Feige,et al.  Maximizing Non-monotone Submodular Functions , 2011 .

[35]  Guillaume Carlier,et al.  OPTIMAL TRANSPORTATION FOR THE DETERMINANT , 2006, math/0612142.

[36]  Yuli Ye,et al.  Max-Sum diversification, monotone submodular functions and dynamic updates , 2012, PODS '12.

[37]  Enric Boix-Adsera,et al.  Wasserstein barycenters can be computed in polynomial time in fixed dimension , 2021, J. Mach. Learn. Res..

[38]  Luca Nenna.  Numerical Methods for Multi-Marginal Optimal Transportation , 2016 .