Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

63126188251 · Jun 202619922001200920172026
48 results for Wasserstein manifold

Rigidity of Wasserstein spaces over Riemannian manifolds

problem Isometric rigidity of L2 Wasserstein spaces over Riemannian manifolds
method Showing L2 Wasserstein spaces are isometrically rigid if and only if their underlying manifolds do not admit a Euclidean de Rham factor
result Isometry of L2 Wasserstein spaces over non-Euclidean manifolds

New method proves absolute continuity of Wasserstein barycenters on manifolds with lower Ricci curvature bound.

problem Proving absolute continuity of Wasserstein barycenters on manifolds with lower Ricci curvature bound.
method Introducing new displacement functionals exploiting Hessian equality and revisiting Souslin space theory, Dunford-Pettis theorem, and de la Vallée Poussin criterion for uniform integrability.
result Absolute continuity of Wasserstein barycenters is established for a general class of manifolds with lower Ricci curvature bound.

Generative flows learn distributions on low-dimensional manifolds robustly via Wasserstein proximals.

problem Learning distributions supported on low-dimensional manifolds robustly.
method Combining Wasserstein-1 and Wasserstein-2 proximal operators to formulate well-posed continuous-time generative flows.
result The combination of Wasserstein-1 and Wasserstein-2 proximals ensures the well-posedness of generative flows, leading to unique and robust learning.

This paper studies geometric properties of Wasserstein metric on SPD(n).

problem Understanding the geometry of symmetric positive-definite matrices under Wasserstein metric.
method Using fiber bundles, the paper derives explicit geometric quantities and proves global properties.
result The manifold is globally geodesic convex with non-negative curvatures but no conjugate pair and cut locus.

Inequalities linking entropy, Fisher info, Stein discrepancy, and Wasserstein distance on Riemannian manifolds.

problem Linking entropy, Fisher info, Stein discrepancy, and Wasserstein distance on Riemannian manifolds.
method Deriving inequalities linking these measures on Riemannian manifolds.
result Strengthening and extending existing inequalities to Riemannian manifolds.

New algorithm accelerates optimization on Riemannian manifolds, including Wasserstein space.

problem Accelerating optimization methods in Riemannian geometry.
method Dynamic stepsize algorithms on Riemannian manifolds with specific vector transport.
result First provable accelerated gradient method in Wasserstein space.

The study examines lower and upper bounds of Wasserstein distances for affine transformations of random vectors.

problem Understanding Wasserstein distances for affine transformations of random vectors.
method Lower and upper bounds for affine transformations of random vectors in Rn\mathbb{R}^n are derived using Bures metric and compositions of affine maps.
result Concrete lower bounds and upper bounds for affine transformations are derived and applied to various distributions.

We study barycenters in the space of probability measures on a Riemannian manifold, equipped with the Wasserstein metric. Under reasonable assumptions, we establish absolute continuity of the barycenter of general measures ΩP(P(M))Ω\in P(P(M)) on Wasserstein space, extending on one hand, results in the Euclidean case (for ba…

2014-12-24abs ↗pdf ↗

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation to a general family of learning objectives including score matching, by observing a new connection …

2020-02-18abs ↗pdf ↗

Study absolute continuity of Wasserstein barycenters on manifolds with singular cost functions.

problem Absolute continuity of Wasserstein barycenters on manifolds with singular cost functions.
method Approximation framework to handle singularity, geometrically transparent.
result Precise analytic condition on cost profile for necessary assumptions.

The paper extends graph-based semi-supervised learning to infinite-dimensional Wasserstein space.

problem Graph-based semi-supervised learning in high-dimensional data.
method Laplace Learning in the Wasserstein space, proving variational convergence and characterizing the Laplace-Beltrami operator.
result Consistent classification performance in high-dimensional settings.

Test partial effects in Frechet regression on Bures-Wasserstein manifolds.

problem Assessing partial effects in Frechet regression on complex manifolds.
method Sample splitting strategy to estimate covariance matrices and test statistic convergence.
result The test statistic converges to a weighted mixture of chi squared components.

The space of Gaussian measures on a Euclidean space is geodesically convex in the L2L^2-Wasserstein space. This space is a finite dimensional manifold since Gaussian measures are parameterized by means and covariance matrices. By restricting to the space of Gaussian measures inside the L2L^2-Wasserstein space, we manag…

2008-01-15abs ↗pdf ↗

The paper develops manifold learning in Wasserstein space for probability measures.

problem Learning latent manifold structure in Wasserstein space of probability measures.
method Introduces submanifolds in Wasserstein space, learns latent structure from samples and distances, recovers tangent spaces via spectral analysis.
result The latent manifold structure can be learned from samples and pairwise extrinsic Wasserstein distances.

Two algorithms estimate Wasserstein distance matrices from few entries for manifold learning.

problem Estimating Wasserstein distance matrices from limited data for manifold learning.
method Proposes two algorithms: matrix completion and Nyström completion for square Wasserstein matrices.
result Nyström completion can outperform matrix completion with a fixed sample budget and improve classification stability.

The paper explores geometric calculations on probability manifolds derived from master equations.

problem Understanding geometric properties of probability manifolds from master equations.
method Deriving geometric quantities like Levi-Civita connection, gradient, Hessian, parallel transport, and curvatures on probability manifolds.
result Calculation of geometric quantities in probability manifolds, including curvatures and connections.

The paper develops stochastic methods on geometric spaces for transformations.

problem Existence and uniqueness of stochastic processes on geometric spaces.
method Stochastic parallel transport and equivariant diffusions on the group of diffeomorphisms.
result Existence and uniqueness of stochastic parallel transport and equivariant diffusions.

Researchers find Busemann functions in Wasserstein space, enabling efficient projections and distances.

problem Defining Busemann functions in Wasserstein space for efficient data projections and distances.
method Investigated existence and computation of Busemann functions in Wasserstein space, establishing closed-form expressions for specific cases.
result Explicit projection schemes for probability distributions on \(\mathbb{R}\) enable novel Sliced-Wasserstein distances over Gaussian mixtures and labeled datasets.

Improves latent space structure for better data representation.

problem Limited ability of conventional priors to encode data manifold structure.
method Introduces an Encoded Prior Sliced Wasserstein AutoEncoder with iterative training and geodesic interpolation.
result Learned manifold encoding preserves topological and geometric properties of data.

The paper shows how heat flows and Wasserstein distances relate to space rigidity.

problem Understanding rigidity in Wasserstein contraction along heat flows.
method Establishing equivalence between rigidity and Bakry-Émery gradient estimates, applying results from Ambrosio-Brué-Semola and Han.
result Spaces with specific curvature bounds exhibit rigidity in Wasserstein contraction.

Nonnegative sectional curvature linked to matrix displacement convexity.

problem Nonnegative sectional curvature in Riemannian manifolds.
method Matrix displacement convexity as a criterion for nonnegative sectional curvature.
result Entropy functional matrix displacement convexity implies nonnegative sectional curvature.

If M is a smooth compact Riemannian manifold, let P(M) denote the Wasserstein space of probability measures on M. If S is an embedded submanifold of M, and μμ is an absolutely continuous measure on S, then we compute the tangent cone of P(M) at μμ.

2014-07-27abs ↗pdf ↗

High-dimensional models trained on smooth manifolds achieve optimal rates in Wasserstein metrics.

problem Training score-based generative models on complex, low-dimensional manifolds.
method Proves optimal rates for SGMs on smooth manifolds, separating into noise regimes and using ReLU nearest-projection coordinates.
result Optimal intrinsic Wasserstein rates are achieved, with polynomial ambient dependence for families with controlled geometry and density.

New method calculates Ricci curvature from distances between weighted volumes.

problem Calculating Ricci curvature for weighted Riemannian manifolds.
method Asymptotic retrieval of generalized Ricci tensor from scaled metric derivatives of Wasserstein 1-distances.
result Limiting coarse curvature of random graphs converges to generalized Ricci tensor.

Adaptive framework for learning latent space dimensions in GANs.

problem Inadequate latent space dimensions lead to poor generative models for complex data.
method Proposes a novel framework (LWGAN) that adaptively learns latent dimensions of data manifolds.
result Proves that the estimated intrinsic dimension is a consistent estimate of the true data manifold dimension.

A new method solves the projection robust Wasserstein distance problem efficiently.

problem Computing the projection robust Wasserstein distance is challenging due to the curse of dimensionality.
method Riemannian block coordinate descent (RBCD) method to solve the regularized max-min problem over the Stiefel manifold.
result RBCD method significantly improves the complexity of obtaining an ε-stationary point compared to existing methods.

This paper raises an implicit manifold learning perspective in Generative Adversarial Networks (GANs), by studying how the support of the learned distribution, modelled as a submanifold Mθ\mathcal{M}_θ, perfectly match with Mr\mathcal{M}_{r}, the support of the real data distribution. We show that optimizing Jensen-Sha…

2017-10-30abs ↗pdf ↗

The paper studies curves in Finsler-like spaces and their properties.

problem Investigating properties of curves in asymmetric metric spaces induced by Finsler structures.
method Analyzes three types of absolutely continuous curves in Finsler-like spaces and establishes the Lisini structure theorem.
result Characterizes the nature of absolutely continuous curves in terms of dynamical transference plans.