Equitable and Optimal Transport with Multiple Agents

We introduce an extension of the Optimal Transport problem when multiple costs are involved. Considering each cost as an agent, we aim to share equally between agents the work of transporting one distribution to another. To do so, we minimize the transportation cost of the agent who works the most. Another point of view is when the goal is to partition equitably goods between agents according to their heterogeneous preferences. Here we aim to maximize the utility of the least advantaged agent. This is a fair division problem. Like Optimal Transport, the problem can be cast as a linear optimization problem. When there is only one agent, we recover the Optimal Transport problem. When two agents are considered, we are able to recover Integral Probability Metrics defined by $\alpha$-Holder functions, which include the widely-known Dudley metric. To the best of our knowledge, this is the first time a link is given between the Dudley metric and Optimal Transport. We provide an entropic regularization of that problem which leads to an alternative algorithm faster than the standard linear program.

[1]  H. Steinhaus,et al.  Sur la division pragmatique , 1949 .

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

[3]  R. M. Dudley,et al.  Weak Convergence of Probabilities on Nonseparable Metric Spaces and Empirical Measures on Euclidean Spaces , 1966 .

[4]  W. Stromquist.  How to Cut a Cake Fairly , 1980 .

[5]  Ton Steerneman,et al.  ON THE TOTAL VARIATION AND HELLINGER DISTANCE BETWEEN SIGNED MEASURES - AN APPLICATION TO PRODUCT MEASURES , 1983 .

[6]  J. Lynch,et al.  A weak convergence approach to the theory of large deviations , 1997 .

[7]  John N. Tsitsiklis,et al.  Introduction to linear optimization , 1997, Athena scientific optimization and computation series.

[8]  A. Müller.  Integral Probability Metrics and Their Generating Classes of Functions , 1997, Advances in Applied Probability.

[9]  Robert E. Tarjan,et al.  Dynamic trees as search trees via euler tours, applied to the network simplex algorithm , 1997, Math. Program..

[10]  C. Villani.  Topics in Optimal Transportation , 2003 .

[11]  Hervé Moulin,et al.  Fair division and collective welfare , 2003 .

[12]  Yurii Nesterov,et al.  Smooth minimization of non-smooth functions , 2005, Math. Program..

[13]  Yoram Singer,et al.  Efficient Learning of Label Ranking by Soft Projections onto Polyhedra , 2006, J. Mach. Learn. Res..

[14]  Marc Teboulle,et al.  A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems , 2009, SIAM J. Imaging Sci..

[15]  H. Brezis.  Functional Analysis, Sobolev Spaces and Partial Differential Equations , 2010 .

[16]  Francis Edward Su,et al.  Two-player envy-free multi-cake division , 2009, Math. Soc. Sci..

[17]  Bernhard Schölkopf,et al.  A Kernel Two-Sample Test , 2012, J. Mach. Learn. Res..

[18]  Gert R. G. Lanckriet,et al.  On the empirical estimation of integral probability metrics , 2012 .

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

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

[21]  Miguel Á. Carreira-Perpiñán,et al.  Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application , 2013, ArXiv.

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

[23]  Arnaud Doucet,et al.  Fast Computation of Wasserstein Barycenters , 2013, ICML.

[24]  Lawrence G. Sager.  Handbook of Computational Social Choice , 2015 .

[25]  Zoubin Ghahramani,et al.  Training generative neural networks via Maximum Mean Discrepancy optimization , 2015, UAI.

[26]  Koby Crammer,et al.  Linear Multi-Resource Allocation with Semi-Bandit Feedback , 2015, NIPS.

[27]  Lirong Xia,et al.  Allocating Indivisible Items in Categorized Domains , 2015, IJCAI.

[28]  A. Dupuy,et al.  Estimating Matching Affinity Matrix Under Low-Rank Constraints , 2016, Information and Inference: A Journal of the IMA.

[29]  Nicolas Courty,et al.  Optimal Transport for Domain Adaptation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Han Zhang,et al.  Improving GANs Using Optimal Transport , 2018, ICLR.

[31]  Gabriel Peyré,et al.  Learning Generative Models with Sinkhorn Divergences , 2017, AISTATS.

[32]  G. Peyré,et al.  Unbalanced optimal transport: Dynamic and Kantorovich formulations , 2015, Journal of Functional Analysis.

[33]  Marco Cuturi,et al.  Subspace Robust Wasserstein distances , 2019, ICML.

[34]  Richard Nock,et al.  A Primal-Dual link between GANs and Autoencoders , 2019, NeurIPS.

[35]  P. Rigollet,et al.  Optimal-Transport Analysis of Single-Cell Gene Expression Identifies Developmental Trajectories in Reprogramming , 2019, Cell.

[36]  J. Zico Kolter,et al.  Wasserstein Adversarial Examples via Projected Sinkhorn Iterations , 2019, ICML.

[37]  Ruilin Li,et al.  Learning to Match via Inverse Optimal Transport , 2018, J. Mach. Learn. Res..

[38]  Tommi S. Jaakkola,et al.  Towards Optimal Transport with Global Invariances , 2018, AISTATS.

[39]  G. Varoquaux,et al.  Comparing distributions: 𝓁1 geometry improves kernel two-sample testing , 2019, NeurIPS 2019.

[40]  Alain Trouvé,et al.  Interpolating between Optimal Transport and MMD using Sinkhorn Divergences , 2018, AISTATS.

[41]  Gabriel Peyré,et al.  Sample Complexity of Sinkhorn Divergences , 2018, AISTATS.

[42]  Yao-Hung Hubert Tsai,et al.  Feature Robust Optimal Transport for High-dimensional Data , 2020, ECML/PKDD.

[43]  H. Zha,et al.  Learning Cost Functions for Optimal Transport , 2020, 2002.09650.

[44]  Hanpin Wang,et al.  Multi-type Resource Allocation with Partial Preferences , 2019, AAAI.

[45]  Marco Cuturi,et al.  Linear Time Sinkhorn Divergences using Positive Features , 2020, NeurIPS.

[46]  Saradha Venkatachalapathy,et al.  Predicting cell lineages using autoencoders and optimal transport , 2020, PLoS Comput. Biol..