The paper provides a concentration result and sample complexity for linear Monge mapping estimation and its application in domain adaptation.
problem Estimating the linear Monge mapping between distributions and its application in domain adaptation.
method The approach involves proving a concentration result and sample complexity for the linear mapping operator, and using it to derive a generalization bound for domain adaptation with optimal transport.
result The method achieves a sample complexity of n−1/2 and approaches the performance of theoretical Bayes predictor under mild conditions. Estimates optimal transport maps with known cost functions.
problem Ensuring optimal transport maps correspond to real-world usefulness.
method Differentiable neural ground costs with known Monge map forms.
result General approach for incorporating prior information.
Study inverse boundary value problem for Monge-Ampère equation on convex domains.
problem Determine a positive source function from the Dirichlet-to-Neumann map for Monge-Ampère equation.
method Recover Hessian as Riemannian metric, prove DN map uniqueness, develop asymptotic expansions, solve nonlocal ∂-equation. result DN map uniquely determines positive source function in convex Euclidean plane domains.
Rolling two hyperboloid surfaces is described using a Monge normal form.
problem Describing the rolling motion of hyperboloid surfaces.
method Parametrization of sl2 using unimodular fractional linear transformations. result Found a Monge normal form for the rolling of hyperboloid surfaces.
New method learns disentangled representations using Gromov-Monge maps.
problem Learning disentangled representations from unlabelled data.
method Introduces a novel approach based on Gromov-Monge maps to preserve geometric features while aligning data distributions.
result Demonstrates effectiveness on four benchmarks, outperforming other methods.
Proposes variational Wasserstein barycenters for geometric clustering.
problem Geometric clustering problems, especially K-means and co-clustering.
method Solves for Monge maps using variational principle, explores connections to K-means and co-clustering.
result Demonstrates feasibility and use of variational Wasserstein barycenters in clustering.
Sharp L∞ estimates proved for complex Monge-Ampère equations.
problem Proving sharp L∞ estimates for complex Monge-Ampère equations. method PDE proof covering fixed and degenerating background metrics, extends to general fully non-linear equations.
result Sharp L∞ estimates proved for complex Monge-Ampère equations. This work introduces methods to compute optimal Monge maps and learn elastic costs for efficient data mapping.
problem Efficiently mapping one probability distribution to another using elastic costs.
method Proposes numerical methods to compute optimal Monge maps and a learning loss for parameterized regularizers.
result Proves the optimality of computed Monge maps and learns the parameters of elastic costs.
These lecture notes are concerned with the solvability of the second boundary value problem of the prescribed affine mean curvature equation and related regularity theory of the Monge-Ampère and linearized Monge-Ampère equations. The prescribed affine mean curvature equation is a fully nonlinear, fourth order, geometri…
Study optimal transport on simplex boundary, proving transport map and potential regularity.
problem Regularity of transport map and potential on simplex boundary.
method Boundary regularity results for optimal transport maps, exploiting simplex symmetries.
result Regularity properties of transport map and its convex potential.
Study of symplectic Monge-Ampère equations using moment maps and contact structures.
problem Characterizing symplectic Monge-Ampère equations through geometric structures.
method Constructing contact cone structures and using moment maps to relate equations to projective spaces.
result The contact cone structure and the cocharacteristic variety coincide for non-degenerate equations.
New framework uses PDE for no-regret generative modeling.
problem Developing efficient generative models for complex distributions.
method Iterative refinement of Brenier maps using mirror gradient descent.
result Converges to optimal Brenier map under various step-size schedules.
Paper proves uniform continuity bounds for complex Monge-Ampère solutions.
problem Estimating the continuity of solutions to complex Monge-Ampère equations.
method PDE-based approach from fully non-linear equations in Kähler geometry.
result Uniform and sharp estimate for the modulus of continuity.
WEGL embeds graphs in a vector space for faster machine learning.
problem Efficiently embedding graphs for machine learning tasks.
method Wasserstein distance for node embedding similarity, Monge maps for graph representation.
result State-of-the-art classification performance with superior computational efficiency.
Proves existence and uniqueness of solutions to a complex equation with gradient term.
problem Existence and uniqueness of solutions to complex Monge-Ampère equation with gradient term.
method Existence and uniqueness proved using complex Hermitian manifolds.
result Existence and uniqueness of solutions proved.
New proof of L∞ estimates for Monge-Ampère and Hessian equations on nef classes.
problem Estimating solutions to Monge-Ampère and Hessian equations on nef classes.
method Applying PDE approach to Kähler manifolds to nef classes.
result New proofs of estimates for Monge-Ampère and Hessian equations.
Uniform bounds derived for fully non-linear equations.
problem Bounding fully non-linear equations uniformly in background metrics.
method Auxiliary Monge-Ampère equations and entropy-like quantities.
result Uniform L∞ bounds for systems coupling fully non-linear equations to their linearizations. The paper studies optimal transport in linear quadratic systems and derives interpolation inequalities.
problem Optimal transport problem in Linear Quadratic optimal control systems.
method Well-posedness of the Monge problem, regularity of optimal transport map, displacement interpolation of measures.
result Derivation of general interpolation inequalities for entropy functionals.
We investigate a class of multi-dimensional two-component systems of Monge-Ampère type that can be viewed as generalisations of heavenly-type equations appearing in self-dual Ricci-flat geometry. Based on the Jordan-Kronecker theory of skew-symmetric matrix pencils, a classification of normal forms of such systems is o…
Paper establishes estimates for solutions on compact manifolds.
problem Solving fully non-linear equations on compact almost Hermitian manifolds.
method Establishes a priori estimates for solutions.
result Solves complex Hessian and Monge-Ampère equations.
Uniform bounds for Green's function on Kähler manifolds derived from complex Monge-Ampère equations.
problem Uniform bounds for Green's function on Kähler manifolds.
method Auxiliary Monge-Ampère equations, non-linear proof.
result Uniform lower bounds for the Green's function on Kähler manifolds.
SOS programming verifies MTW tensor non-negativity for optimal transport maps.
problem Verifying MTW tensor non-negativity for general cost functions is difficult.
method Sum-of-Squares (SOS) programming for verifying and approximating MTW non-negativity.
result SOS programming provides certificates and approximations of MTW non-negativity.
We present a deep generative model, named Monge-Ampère flow, which builds on continuous-time gradient flow arising from the Monge-Ampère equation in optimal transport theory. The generative map from the latent space to the data space follows a dynamical system, where a learnable potential function guides a compressible…
Proves C^2,alpha estimates for elliptic equations on hyperkähler manifolds.
problem Elliptic equations on hypercomplex manifolds.
method Proves C^2,alpha estimates under suitable assumptions.
result Solutions to specific elliptic equations on hyperkähler manifolds satisfy C^2,alpha estimates.
The flow converges without Kähler-Einstein and develops ideal sheaves.
problem Analyzing convergence of inverse Monge-Ampere flow without Kähler-Einstein metrics.
method Generalizing the flow and providing conditions for convergence and ideal sheaves development.
result The flow converges without Kähler-Einstein metrics and develops Nadel multiplier ideal sheaves.
Paper establishes estimates for nonlinear equations on compact manifolds.
problem Estimating solutions to fully nonlinear equations with gradient terms on compact almost Hermitian manifolds.
method Establishes second order estimates and proves existence of solutions for specific equations.
result Proves existence of solutions for various equations, including Monge-Ampère and Hessian equations.
New classification of hyperbolic Monge-Ampère systems with S1=0.
problem Characterizing hyperbolic Monge-Ampère systems with S1=0. method Analyzing invariant tensors S1 and S2 to classify systems with S1=0. result All S1=0 systems with cohomogeneity at most one are linear up to contact transformations. All second order scalar differential invariants of symplectic hyperbolic and elliptic Monge-Ampère equations with respect to symplectomorphisms are explicitly computed. In particular, it is shown that the number of independent second order invariants is equal to 7, in sharp contrast with general Monge-Ampère equations …
In this lecture delivered at the Integrable and Quantum Field Theory at Peyresq sixth meeting, we review the Lychagin's Monge-Ampere operators theory and exhibit the link it establishes between the classical problem of local equivalence for non linear partial differential equations and the problem of integrability of s…
Auxiliary equations improve bounds in symplectic geometry.
problem Improving bounds for the Calabi-Yau equation.
method Adapted Monge-Ampère equations for symplectic geometry.
result Reduced the bound from exponential to L1. Uniform bounds for complex equations using Monge-Ampère method.
problem Bounding solutions to complex equations.
method Auxiliary Monge-Ampère equation method.
result Uniform bounds remain valid even as background metrics degenerate.
This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularize…
Develop a framework for barycentric projections of optimal transport plans on Riemannian manifolds.
problem Optimal transport couplings are probabilistic objects, while many learning pipelines require deterministic maps.
method Develop a framework for barycentric projections of transport couplings on Riemannian manifolds.
result The intrinsic projection maps each source point to the conditional Fréchet mean of its destination law and is shown to be the best deterministic representative under squared geodesic loss.
In the neighborhood of a regular point, generalized Kahler geometry admits a description in terms of a single real function, the generalized Kahler potential. We study the local conditions for a generalized Kahler manifold to be a generalized Calabi-Yau manifold and we derive a non-linear PDE that the generalized Kahle…
Unified framework for implicit generative models with theoretical guarantees.
problem Learning implicit generative models with theoretical guarantees.
method Integrating optimal transport, numerical ODE, density-ratio estimation, and deep neural networks.
result Unified framework with theoretical guarantees for implicit generative learning.
Optimal transport explored on a specific geometric space.
problem Optimal transport problem in sub-Lorentzian Heisenberg group.
method Synthetic metric spacetime structure analysis and sub-Lorentzian version of Brenier's theorem.
result Established sub-Lorentzian version of Brenier's theorem and derived Monge-Ampère equation.
This work builds the connection between the regularity theory of optimal transportation map, Monge-Ampère equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse. According to the regularity theory of Monge-Ampère equation, if the support of the …
We come up with infinite-dimensional prequantum line bundles and moment map interpretations of three different sets of equations - the generalised Monge-Amp`ere equation, the almost Hitchin system, and the Calabi-Yang-Mills equations. These are all perturbations of already existing equations. Our construction for the g…
A new method to estimate optimal transport maps without constraints.
problem Challenges in fitting optimal transport maps with neural networks.
method Introducing a Monge gap regularizer to estimate OT maps without architectural constraints.
result The proposed method significantly outperforms other baselines in practice.
Study on m-positivity in Kähler manifolds with new Monge-Ampère-type equation.
problem Exploring m-positivity in Kähler manifolds and its geometric applications. method Generalizing pseudo-effective and big Bott-Chern cohomology classes, proposing a new Monge-Ampère-type equation.
result Proof of a form of uniqueness for solutions of the Monge-Ampère-type equation.
This note exposes the differential topology and geometry underlying some of the basic phenomena of optimal transportation. It surveys basic questions concerning Monge maps and Kantorovich measures: existence and regularity of the former, uniqueness of the latter, and estimates for the dimension of its support, as well …
Let u be a function of n independent variables x^1, ..., x^n, and U=(u_{ij}) the Hessian matrix of u. The symplectic Monge-Ampere equation is defined as a linear relation among all possible minors of U. Particular examples include the equation det U=1 governing improper affine spheres and the so-called heavenly equatio…
Solves complex Monge-Ampère equation for (p,p)-forms on Kähler manifolds.
problem Existence and uniqueness of smooth solutions for differential (p,p)-forms on compact Kähler manifolds. method Introduced a complex Monge-Ampère equation for (p,p)-forms, showed existence and uniqueness, defined a geometric flow preserving cohomology classes. result Existence and uniqueness of smooth solutions for differential (p,p)-forms on compact Kähler manifolds for 1≤p<n. The purpose of this paper is to show that in a finite dimensional metric space with Alexandrov's curvature bounded below, Monge's transport problem for the quadratic cost admits a unique solution.
Generative sampler learns velocity fields for efficient posterior inference.
problem Sampling from complex posterior distributions in high dimensions.
method Generative multivariate posterior sampler via flow matching, learning a velocity field for a deterministic transport map.
result Conditional Brenier map enables fast generation of credible sets with theoretical consistency guarantees.
Paper develops a framework for hyperbolic Monge-Ampère equation on strips, proving well-posedness and stability.
problem Addressing the rigidity-flexibility dichotomy for wrinkled patterns in thin elastic sheets.
method Develops hodograph transformation and parametrix-corrector decomposition to handle corner singularities and prove well-posedness.
result Proves existence and uniqueness of hodograph weak solutions and derives energy estimates for stability.
We give a new probabilistic construction of solutions to real Monge-Ampère equations in R^n satisfying the second boundary value problem with respect to a given target convex body P) which fits naturally into the theory of optimal transport. More precisely, certain beta-deformed permanental (bosonic) N-particle point p…
We extend the Mason-Newman Lax pair for the elliptic complex Monge-Ampère equation so that this equation itself emerges as an algebraic consequence. We regard the function in the extended Lax equations as a complex potential. We identify the real and imaginary parts of the potential, which we call partner symmetries, w…