Pseudo-Riemannian geometry encodes information geometry in optimal transport
From MaRDI portal
Publication:2154658
DOI10.1007/S41884-021-00053-7zbMATH Open1493.49049arXiv1906.00030OpenAlexW3194068170WikidataQ115371031 ScholiaQ115371031MaRDI QIDQ2154658FDOQ2154658
Ting-Kam Leonard Wong, Jiaowen Yang
Publication date: 20 July 2022
Published in: Information Geometry (Search for Journal in Brave)
Abstract: Optimal transport and information geometry both study geometric structures on spaces of probability distributions. Optimal transport characterizes the cost-minimizing movement from one distribution to another, while information geometry originates from coordinate-invariant properties of statistical inference. Their connections and applications in statistics and machine learning have started to gain more attention. In this paper we give a new differential geometric connection between the two fields. Namely, the pseudo-Riemannian framework of Kim and McCann, a geometric perspective on the fundamental Ma-Trudinger-Wang (MTW) condition in the regularity theory of optimal transport maps, encodes the dualistic structure of statistical manifold. This general relation is described using the natural framework of -divergence, a divergence defined by an optimal transport map. As a by-product, we obtain a new information-geometric interpretation of the MTW tensor. This connection sheds light on old and new aspects of information geometry. The dually flat geometry of Bregman divergence corresponds to the quadratic cost and the pseudo-Euclidean space, and the -divergence introduced by Pal and the first author has constant sectional curvature in a sense to be made precise. In these cases we give a geometric interpretation of the information-geometric curvature in terms of the divergence between a primal-dual pair of geodesics.
Full work available at URL: https://arxiv.org/abs/1906.00030
Recommendations
optimal transportBregman divergenceinformation geometrylogarithmic divergencepseudo-Riemannian geometryMa-Trudinger-Wang tensor\(c\)-divergence
Optimal transportation (49Q22) Information theory (general) (94A15) Information geometry (statistical aspects) (62B11)
Cites Work
- Computational Optimal Transport: With Applications to Data Science
- The geometry of optimal transportation
- Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
- Polar factorization and monotone rearrangement of vector‐valued functions
- Optimal Transport
- On the regularity of solutions of optimal transportation problems
- Regularity of potential functions of the optimal transportation problem
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Regularity of optimal maps on the sphere: the quadratic cost and the reflector antenna
- Second order efficiency of minimum contrast estimators in a curved exponential family
- A infinite-dimensional geometric structure on the space of all the probability measures equivalent to a given one
- Title not available (Why is that?)
- The Monge–Ampère equation and its link to optimal transportation
- Towards a canonical divergence within information geometry
- Information-Theoretic Differential Geometry of Quantum Phase Transitions
- Information geometry of \(q\)-Gaussian densities and behaviors of solutions to related diffusion equations
- A survey of the Schrödinger problem and some of its connections with optimal transport
- An interpolating distance between optimal transport and Fisher-Rao metrics
- Continuity, curvature, and the general covariance of optimal transportation
- The geometry of relative arbitrage
- Title not available (Why is that?)
- On the second boundary value problem for Monge-Ampère type equations and optimal transportation
- Optimization of relative arbitrage
- Pseudo-Riemann geometry calibrates optimal transportation
- A glimpse into the differential topology and geometry of optimal transport
- Information geometry and its applications
- Logarithmic divergences: geometry and interpretation of curvature
- Exponentially concave functions and a new information geometry
- Natural gradient via optimal transport
- Information Geometry
- Information Geometry in Portfolio Theory
- Divergence functions in information geometry
- Information geometry connecting Wasserstein distance and Kullback-Leibler divergence via the entropy-relaxed transportation problem
- Logarithmic divergences from optimal transport and Rényi geometry
- Embedding optimal transports in statistical manifolds
- Multiplicative Schrödinger problem and the Dirichlet transport
- Geometry of matrix decompositions seen through optimal transport and information geometry
- Geometric Modeling in Probability and Statistics
- The Kähler geometry of certain optimal transport problems
- Statistical Manifolds Admitting Torsion and Partially Flat Spaces
- Information Geometry for Regularized Optimal Transport and Barycenters of Patterns
Cited In (6)
- Conformal mirror descent with logarithmic divergences
- Geometric thermodynamics for the Fokker-Planck equation: stochastic thermodynamic links between information geometry and optimal transport
- First and second derivative Hölder estimates for generated Jacobian equations
- A geometric Laplace method
- Information geometry of Wasserstein statistics on shapes and affine deformations
- When optimal transport meets information geometry
This page was built for publication: Pseudo-Riemannian geometry encodes information geometry in optimal transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2154658)
