Quantum probability metrics improve distribution comparison in high dimensions.
problem Challenges in comparing probability distributions, especially in high-dimensional and non-compact domains.
method Quantum probability metrics (QPMs) derived from quantum state spaces, overcoming limitations of MMD.
result QPMs offer enhanced sensitivity to subtle distributional differences in high dimensions and improve performance in generative modeling.
A new metric for comparing probability measures on graphs, scalable and negative definite.
problem Optimal transport's high complexity and indefiniteness for kernel machines.
method Sobolev transport metric for graph metrics, closed-form formula, negative definiteness.
result Sobolev transport yields a scalable and negative definite metric.
Permutation invariant network learns Wasserstein metrics.
problem Understanding the space of probability measures and comparing distributions.
method Permutation invariant network mapping samples to a low-dimensional space.
result Network can generalize to compute distances between unseen densities and learn moments.
The paper explores geometry of probability measures and barycenter maps.
problem Understanding the space of probability measures and their barycenter.
method Information geometry, Fisher metric, dualistic structures, divergences, geodesics.
result Recent developments in the geometry of probability measures and barycenter.
A new method for optimization in probability space using Newton's flows.
problem Optimization in probability space with information metrics.
method Information Newton's flows, including Fisher-Rao and Wasserstein-2 metrics, with Newton's Langevin dynamics and variational methods.
result Effective numerical implementation and convergence results for the proposed method.
NNLMs optimize poorly for word probabilities due to embedding space structure.
problem NNLMs assign suboptimal probabilities to some words.
method Analyzed the inductive bias of NNLMs and the structure of word embeddings.
result Words on the convex hull have bounded probability, affecting others.
We formulate the Riemannian calculus of the probability set embedded with L2-Wasserstein metric. This is an initial work of transport information geometry. Our investigation starts with the probability simplex (probability manifold) supported on vertices of a finite graph. The main idea is to embed the probability m…
The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis. This paper provides upper and lower bounds on statistical minimax rates for the problem of estimating a probability distribution under W…
The geometric approach to optimal transport and information theory has triggered the interpretation of probability densities as an infinite-dimensional Riemannian manifold. The most studied Riemannian structures are Otto's metric, yielding the L2-Wasserstein distance of optimal mass transport, and the Fisher--Rao me…
A new pseudo-metric uses data depth to compare probability distributions.
problem Designing a metric between probability distributions for machine learning applications.
method Extension of univariate quantiles to multivariate spaces, using data depth and Hausdorff distance.
result The pseudo-metric is robust, factorizes translations, and has good behavior under transformations.
New theory approximates functions between metric spaces using random probability measures.
problem Building universal functions approximators between arbitrary metric spaces.
method Using elementary functions between Euclidean spaces, randomization to output discrete probability measures over target space.
result Very general qualitative guarantees and quantitative guarantees for Hölder-like maps.
Gromov-Wasserstein (GW) is a powerful tool to compare probability measures whose supports are in different metric spaces. GW suffers however from a computational drawback since it requires to solve a complex non-convex quadratic program. We consider in this work a specific family of cost metrics, namely \textit{tree me…
Implementing k-NN classification using Gromov--Wasserstein distances
problem Comparing metric measure spaces
method Gromov--Wasserstein and fused Gromov--Wasserstein distances
result Universal consistency of k-NN classifiers Study shows zero probability of cut locus for Fréchet mean on Riemannian manifolds.
problem Understanding the cut locus of Fréchet mean on Riemannian manifolds.
method Analytical proof and examples.
result Cut locus of Fréchet mean has zero probability.
New dimension concept for groups based on percolation probability.
problem Defining a new dimension for groups using percolation probability.
method Introducing percolation dimension pdim(G) for groups G using symmetric probability measures. result The percolation dimension pdim(G) has natural properties like monotonicity and coincides with growth rate exponents for various groups. New metrics avoid high-dimensional analysis challenges, proving convergence without 'curse of dimensionality'.
problem High-dimensional analysis challenges in empirical measure convergence.
method Proposed a new class of probability metrics free of the curse of dimensionality.
result Convergence of empirical measures is free of the curse of dimensionality.
In this article, we study the geodesic problem in a generalized metric space, in which the distance function satisfies a relaxed triangle inequality d(x,y)≤σ(d(x,z)+d(z,y)) for some constant σ≥1, rather than the usual triangle inequality. Such a space is called a quasimetric space. We show that many well-kn…
A new metric based on hitting probabilities for directed graphs and Markov chains.
problem Lack of metrics specifically adapted to asymmetric structure of directed graphs and Markov chains.
method Metric based on hitting probabilities, insensitive to shortest and average walk distances.
result New structural theory of directed graphs and utility for various applications.
A new method estimates multi-dimensional value distributions using Hilbert space embeddings.
problem Estimating value distributions in complex, multi-dimensional reinforcement learning settings.
method Hilbert space mappings and kernel mean embeddings to estimate the kernel mean embedding of multi-dimensional value distributions.
result Uniform convergence guarantees and robust off-policy evaluation demonstrated in simulations.
E2M predicts metric space outputs using deep learning.
problem Predicting non-Euclidean outputs like distributions and matrices.
method Weighted Fréchet means over learned weights.
result E2M achieves state-of-the-art performance across various outputs.
Let S be a non-exceptional oriented surface of finite type. We discuss the action of subgroups of the mapping class group of S on the CAT(0)-boundary of the completion of Teichmueller space with respect to the Weil-Petersson metric. We show that the set of invariant Borel probability measures for the Weil-Petersson flo…
Central limit theorem for Green metrics on hyperbolic groups.
problem Proving a central limit theorem for Green metrics on hyperbolic groups.
method Proving a central limit theorem for Green metrics on hyperbolic groups using probability measures and ordering elements.
result Proved a central limit theorem for Green metrics on hyperbolic groups.
New metric for probability measures connects physics and geometry.
problem Developing a new metric for probability measures.
method Transport Hessian metric, formulated dynamical systems.
result Connections to physics equations and mathematical models.
On a closed manifold of dimension greater than one, every smooth weak Riemannian metric on the space of smooth positive probability densities, that is invariant under the action of the diffeomorphism group, is a multiple of the Fisher--Rao metric.
Random covers of hyperbolic surfaces follow a specific probability measure.
problem Understanding the distribution of random covers of hyperbolic surfaces.
method Analyzing random covers subject to specific group isomorphism conditions.
result Asymptotic distribution of random covers according to a probability measure on moduli space of metric graphs.
This paper studies gradient flows for sampling using various metrics and their affine invariance.
problem Sampling from probability distributions with unknown normalizations.
method Gradient flows in the space of probability measures, focusing on Kullback-Leibler divergence and affine invariance of metrics.
result Gradient flows of Kullback-Leibler divergence do not depend on the normalization constant, and affine invariance is achieved for certain metrics.
New KQEs improve probability metrics without mean function constraints.
problem Improving probability metrics without relying on mean function representations.
method Kernel quantile embeddings (KQEs) to construct new distances.
result KQEs offer a competitive alternative to MMD with near-linear cost.
New invariant metrics preserved under deformed Markov embeddings.
problem Preserving invariance in probability measure spaces under deformed embeddings.
method Deforming Markov embeddings while maintaining sufficiency, proving existence and uniqueness of invariant families.
result Existence and uniqueness of invariant families of tensor fields under deformed embeddings.
This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. that minimizes a total cost of transporting probability masses) that unveils the geometric nature of …
Paper proposes new density estimators for high-dimensional data.
problem Prohibitive computational cost and slow convergence rate in high-dimensional density estimation.
method Adaptive hyperbolic cross density estimators in mixed smooth Sobolev spaces.
result Proposed estimators do not suffer curse of dimensionality under Integral Probability Metrics.
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing, and independence testing. This embedding represents any probability measure as a mean element in a reproducing kernel Hilbert space (RKHS). A pseudometric on the spac…
Study of random sections on complex spaces converging to equilibrium metrics.
problem Understanding the behavior of random holomorphic sections on complex spaces.
method Analyzing the convergence of normalized Fubini-Study currents and integration currents to the equilibrium metric's curvature.
result The normalized currents of integration along zero divisors converge almost surely to the curvature current of the equilibrium metric.
Optimizes functionals on probability space using ICNNs.
problem Optimizing functionals on the space of probabilities with high-dimensional convex functions.
method Proposes an approach using input-convex neural networks (ICNNs) to approximate the JKO scheme.
result Demonstrates feasibility and validity in approximating solutions of PDEs and molecular discovery.
We prove the existence of a quantum isometry groups for new classes of metric spaces: (i) geodesic metrics for compact connected Riemannian manifolds (possibly with boundary) and (ii) metric spaces admitting a uniformly distributed probability measure. In the former case it also follows from recent results of the secon…
We introduce a weak notion of barycenter of a probability measure μ on a metric measure space (X,d,m), with the metric d and reference measure m. Under the assumption that optimal transport plans are given by mappings, we prove that our barycenter B(μ) is well defined; it is a probability measur…
A simpler proof shows L2-metric completion is CAT(0).
problem Completing Riemannian metrics space.
method Easier proof of existing result by Brian Clarke.
result Completion of Riemannian metrics is CAT(0).
New geometric interpretation of Amari-Cencov α-connections on probability densities.
problem Geometric interpretation of Amari-Cencov α-connections on probability densities.
method Riemannian metrics and Levi-Civita connections.
result Geodesics of α-connections are energy-minimizing curves.
New bounds use IPMs to improve generalization in machine learning.
problem Improving generalization bounds in machine learning.
method PAC-Bayes bounds with Integral Probability Metrics (IPM).
result Natural interpolation between worst-case and favorable cases.
WWe define the notion of a random metric space and prove that with probability one such a space is isometricto the Urysohn universal metric space. The main technique is the study of universal and random distance matrices; we relate the properties of metric (in particulary universal) space to the properties of distance …
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.
Formula derived for curvature in measure spaces.
problem Deriving sectional curvature in measure spaces.
method Explicit formula derivation for sectional curvature in M(M) with metrics HK and W2. result Curvature analysis in M(M) reveals both negative and positive components. We introduce an universum of the Polish (=complete separable metric) space - the convex cone of distance matrices and study its geometry. It happened that the generic Polish spaces in this sense of this universum is so called Urysohn spaces defined by P.S.Urysohn in 20-th, and generic metric triple (= metric space with…
The paper provides statistical guarantees for generative models using dimension reduction.
problem Improving the quality of generative models without increasing dimensionality.
method Modeling generative devices as smooth transformations of a lower-dimensional space and using integral probability metrics.
result Established a risk bound showing the impact of dimension reduction on generative model error.
The paper studies the geometry of probability measures on the unit circle.
problem Understanding the Riemannian geometry of probability measures on the unit circle.
method Developed an intrinsic framework using the Peter-Weyl Theorem to study the differential geometry of Wasserstein spaces of compact Lie groups.
result Explicitly demonstrated that the Wasserstein space of the unit circle is flat with vanishing curvature.
It is shown that bootstrap approximations of an estimator which is based on a continuous operator from the set of Borel probability measures defined on a compact metric space into a complete separable metric space is stable in the sense of qualitative robustness. Support vector machines based on shifted loss functions …
We associate certain probability measures on R to geodesics in the space $\H_L$ of positively curved metrics on a line bundle L, and to geodesics in the finite dimensional symmetric space of hermitian norms on H0(X,kL). We prove that the measures associated to the finite dimensional spaces converge weakly to t…
We study the heat equation on time-dependent metric measure spaces (as well as the dual and the adjoint heat equation) and prove existence, uniqueness and regularity. Of particular interest are properties which characterize the underlying space as a super Ricci flow as previously introduced by the second author. Our ma…
Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete probability distributions in a Wasserstein space, endowed with an optimal transport metri…