Quadratically Regularized Optimal Transport: Existence and Multiplicity of Potentials
Abstract: The optimal transport problem with quadratic regularization is useful when sparse couplings are desired. The density of the optimal coupling is described by two functions called potentials; equivalently, potentials can be defined as a solution of the dual problem. We prove the existence of potentials for a general square-integrable cost. Potentials are not necessarily unique, a phenomenon directly related to sparsity of the optimal support. For discrete problems, we describe the family of all potentials based on the connected components of the support, for a graph-theoretic notion of connectedness. On the other hand, we show that continuous problems have unique potentials under standard regularity assumptions, regardless of sparsity. Using potentials, we prove that the optimal support is indeed sparse for small regularization parameter in a continuous setting with quadratic cost, which seems to be the first theoretical guarantee for sparsity in this context.
- Stability and sample complexity of divergence regularized optimal transport. Preprint arXiv:2212.00367v1, 2022.
- Entropic optimal transport: Geometry and large deviations. Duke Math. J., 171(16):3363–3400, 2022.
- Smooth and sparse optimal transport. volume 84 of Proceedings of Machine Learning Research, pages 880–889, 2018.
- V. I. Bogachev. Measure Theory. Vol. I. Springer-Verlag, Berlin, 2007.
- V. I. Bogachev. Measure Theory. Vol. II. Springer-Verlag, Berlin, 2007.
- Decomposition of multivariate functions. Canad. J. Math., 44(3):463–482, 1992.
- Convergence rate of general entropic optimal transport costs. Calc. Var. Partial Differential Equations, 62(4):Paper No. 116, 28, 2023.
- M. Cuturi. Sinkhorn distances: Lightspeed computation of optimal transport. In Advances in Neural Information Processing Systems 26, pages 2292–2300. 2013.
- Regularized optimal transport and the rot mover’s distance. J. Mach. Learn. Res., 19(15):1–53, 2018.
- S. Di Marino and A. Gerolin. Optimal transport losses and Sinkhorn algorithm with general convex regularization. Preprint arXiv:2007.00976v1, 2020.
- S. Eckstein and M. Kupper. Computation of optimal transport and related hedging problems via penalization and neural networks. Appl. Math. Optim., 83(2):639–667, 2021.
- S. Eckstein and M. Nutz. Convergence rates for regularized optimal transport via quantization. Math. Oper. Res., 49(2):1223–1240, 2024.
- M. Essid and J. Solomon. Quadratically regularized optimal transport on graphs. SIAM J. Sci. Comput., 40(4):A1961–A1986, 2018.
- H. Föllmer. Random fields and diffusion processes. In École d’Été de Probabilités de Saint-Flour XV–XVII, 1985–87, volume 1362 of Lecture Notes in Math., pages 101–203. Springer, Berlin, 1988.
- H. Föllmer and N. Gantert. Entropy minimization and Schrödinger processes in infinite dimensions. Ann. Probab., 25(2):901–926, 1997.
- H. Föllmer and A. Schied. Stochastic Finance: An Introduction in Discrete Time. W. de Gruyter, Berlin, 3rd edition, 2011.
- Infinitesimal behavior of quadratically regularized optimal transport and its relation with the porous medium equation. Preprint arXiv:2407.21528v1, 2024.
- Stochastic optimization for large-scale optimal transport. In Advances in Neural Information Processing Systems 29, pages 3440–3448, 2016.
- N. Gigli and L. Tamanini. Second order differentiation formula on RCD∗(K,N)superscriptRCD𝐾𝑁{\mathrm{RCD}}^{*}(K,N)roman_RCD start_POSTSUPERSCRIPT ∗ end_POSTSUPERSCRIPT ( italic_K , italic_N ) spaces. J. Eur. Math. Soc. (JEMS), 23(5):1727–1795, 2021.
- A. González-Sanz and M. Nutz. Quantitative convergence of quadratically regularized linear programs. Preprint arXiv:2408.04088v1, 2024.
- A. González-Sanz and M. Nutz. Sparsity of quadratically regularized optimal transport: Scalar case. Preprint arXiv:2410.03353v1, 2024.
- Monotonicity in quadratically regularized linear programs. Preprint arXiv:2408.07871v1, 2024.
- Improved training of Wasserstein GANs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 5769–5779, 2017.
- Continuous regularized Wasserstein barycenters. In H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 17755–17765. Curran Associates, Inc., 2020.
- D. Lorenz and H. Mahler. Orlicz space regularization of continuous optimal transport problems. Appl. Math. Optim., 85(2):Paper No. 14, 33, 2022.
- Quadratically regularized optimal transport. Appl. Math. Optim., 83(3):1919–1949, 2021.
- H. Malamut and M. Sylvestre. Convergence rates of the regularized optimal transport: Disentangling suboptimality and entropy. Preprint arXiv:2306.06940v1, 2023.
- Nonlinear perturbation of linear programs. SIAM J. Control Optim., 17(6):745–752, 1979.
- M. Nutz. Introduction to Entropic Optimal Transport. Lecture notes, Columbia University, 2021. https://www.math.columbia.edu/~mnutz/docs/EOT_lecture_notes.pdf.
- M. Nutz and J. Wiesel. Entropic optimal transport: convergence of potentials. Probab. Theory Related Fields, 184(1-2):401–424, 2022.
- Limits of semistatic trading strategies. Math. Finance, 33(1):185–205, 2023.
- OptimalTransport.jl. Optimaltransport.quadreg, 2023. https://juliaoptimaltransport.github.io/OptimalTransport.jl/dev/#Quadratically-regularised-optimal-transport [Accessed 12/01/2023].
- G. Peyré and M. Cuturi. Computational optimal transport: With applications to data science. Foundations and Trends in Machine Learning, 11(5-6):355–607, 2019.
- Python Optimal Transport. ot.stochastic.loss_dual_quadratic, 2023. https://pythonot.github.io/gen_modules/ot.stochastic.html#id22 [Accessed 12/01/2023].
- L. Qi. The maximal normal operator space and integration of subdifferentials of nonconvex functions. Nonlinear Anal., 13(9):1003–1011, 1989.
- L. Rüschendorf and W. Thomsen. Closedness of sum spaces and the generalized Schrödinger problem. Teor. Veroyatnost. i Primenen., 42(3):576–590, 1997.
- B. Schmitzer. Stabilized sparse scaling algorithms for entropy regularized transport problems. SIAM J. Sci. Comput., 41(3):A1443–A1481, 2019.
- Large scale optimal transport and mapping estimation. In International Conference on Learning Representations, 2018.
- C. Villani. Optimal transport, old and new, volume 338 of Grundlehren der Mathematischen Wissenschaften. Springer-Verlag, Berlin, 2009.
- J. Wiesel and X. Xu. Sparsity of quadratically regularized optimal transport: Bounds on concentration and bias. Preprint arXiv:2410.03425v1, 2024.
- Manifold learning with sparse regularised optimal transport. Preprint arXiv:2307.09816v1, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.