In this paper, we study non integrable distributions in a Riemannian manifold with a semi-symmetric metric connection, a semi-symmetric non-metric connection and a statistical connection. We obtain the Gauss, Codazzi, and Ricci equations for non integrable distributions with respect to the semi-symmetric metric connect…
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.
168,694 papers · 148 categories
Trend · papers per month
48 results for “Distribution metrics”
Paper explores how text generation quality and diversity metrics relate to distribution fitting.
problem Unclear relation between text generation quality and diversity metrics and distribution fitting.
method Theoretical approach to prove a linear combination of quality and diversity metrics can be a divergence metric.
result CR/NRR proposed as a better substitute for BLEU/Self-BLEU metrics.
Study variational problem on manifold with special distributions.
problem Generalize Einstein metrics on manifold with multiple distributions.
method Define functional of pseudo-Riemannian metric and contorsion tensor, prove critical pairs make distributions totally umbilical.
result Metrics in critical pairs make all distributions totally umbilical.
New metrics improve regression evaluation across different data distributions.
problem Difficulty in comparing regression evaluations across datasets with varying distributions.
method Modification of regression metrics by weighting with the inverse distribution of function values or samples using a Gaussian kernel density estimator.
result New metrics are less sensitive to changing distributions, especially when correcting by the marginal distribution in .
Study finds homogeneous spaces with geodesic orbits but no integrable distributions.
problem Characterizing homogeneous spaces with specific geometric properties.
method Examined Lie groups with compact stabilizers and classified spaces based on geodesic orbits and integrable distributions.
result Identified homogeneous spaces with geodesic orbits but lacking integrable invariant distributions.
Study para-Kähler-Einstein metrics and their non-integrable twistor distributions.
problem Characterize para-Kähler-Einstein metrics and their associated non-integrable twistor distributions.
method Use Cartan's method of equivalence and analyze the anti-self-dual Weyl tensor.
result Establish a correspondence between the anti-self-dual Weyl tensor and the Cartan quartic of the twistor distribution.
Deep metric learning employs deep neural networks to embed instances into a metric space such that distances between instances of the same class are small and distances between instances from different classes are large. In most existing deep metric learning techniques, the embedding of an instance is given by a featur…
The present paper is devoted to the problem of (local) geodesic equivalence of Riemannian metrics and sub-Riemannian metrics on generic corank 1 distributions. Using Pontryagin Maximum Principle, we treat Riemannian and sub-Riemannian cases in an unified way and obtain some algebraic necessary conditions for the geodes…
Sharp bounds for distortion risk metrics under uncertain distributions.
problem Modeling risk metrics under distributional uncertainty.
method Established bounds for distortion risk metrics using specific features of underlying distributions.
result Identified worst- and best-case values of distortion risk metrics.
Study on geometry of Dirichlet distributions using Fisher-Rao metric.
problem Understanding the geometry of Dirichlet distributions.
method Analysis of Fisher-Rao metric on Dirichlet distribution parameter space.
result Geodesic completeness and negative sectional curvature of the space.
We show that any generalised smooth distribution on a smooth manifold, possibly of non-constant rank, admits a Riemannian metric. Using such a metric, we attach a Laplace operator to any smooth distribution as such. When the underlying manifold is compact, we show that it is essentially self-adjoint. Viewing this Lapla…
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.
Proposes DWMD for better matching of hidden representations across domains.
problem Measuring data distribution discrepancy between semantically related domains for feature representation matching.
method DWMD, a moment-based probability distribution metric that explicitly orders and weights higher-order moments.
result DWMD is error-free and can strictly reflect distribution differences without feature distribution assumptions.
Study compares synthetic and distributional Ricci curvature bounds.
problem Comparing synthetic and distributional approaches to lower Ricci curvature bounds.
method Analyzes synthetic via weak displacement convexity and distributional via non-negativity of Ricci-tensor.
result Distributional bounds imply entropy bounds for metrics and vice versa for under convergence condition.
Study on null-projectability of Levi-Civita connections in neutral metrics.
problem Characterizing projectability of Levi-Civita connections along null parallel distributions.
method Analyzing projectability of torsion-free connections along foliations on manifolds, focusing on neutral metric signatures and mid-dimensional distributions.
result Extension of Patterson and Walker's Riemann extension metrics to null parallel distributions of any dimension.
New bounds for low-regularity Riemannian metrics defined via distributional curvature.
problem Establishing curvature bounds for Riemannian metrics of low regularity.
method Introducing a distributional version of sectional curvature for and metrics.
result New bounds for low-regularity metrics recover classical bounds in Alexandrov spaces.
In this paper we consider the space of those probability distributions which maximize the -Rényi entropy. These distributions have the same parameter space for every , and in the case these are the normal distributions. Some methods to endow this parameter space with Riemannian metric is presented: the seco…
The multivariate normal density is a monotonic function of the distance to the mean, and its ellipsoidal shape is due to the underlying Euclidean metric. We suggest to replace this metric with a locally adaptive, smoothly changing (Riemannian) metric that favors regions of high local density. The resulting locally adap…
In this paper, the HyperKahler contact distribution of a 3-Sasakian manifold is studied. To analyze the curvature properties of this distribution, the special metric connection is defined. This metric connection is completely determined by HyperKahler contact distribution. We prove that HyperKahler conta…
New HyperKahler structure found for 3-contact distributions on Sasakian manifolds.
problem Finding a HyperKahler structure for 3-contact distributions on Sasakian manifolds.
method Defined a special metric connection and proved curvature properties.
result 3-Sasakian manifolds with constant -sectional curvatures have constant holomorphic sectional curvatures in their HyperKahler contact distribution.
The study defines and analyzes semi-invariant submanifolds in complex contact metric manifolds.
problem Characterizing semi-invariant submanifolds in complex contact metric manifolds.
method Definition and derivation of relations, integrability conditions of distributions.
result Obtained useful relations and integrability conditions for semi-invariant submanifolds.
Metrics assess uncertainty structure and distribution for regression models.
problem Quantifying uncertainty in high-dimensional and nonlinear regression tasks.
method Two bounded comparison metrics for uncertainty structure and distribution.
result DNNs and DNOs provide encouraging uncertainty metric values in high dimensions.
Unified deep metric learning approach using neural networks.
problem Learning embeddings of data and extending Euclidean distances.
method Deep Bregman divergences based on neural networks.
result Superior performance on benchmark datasets compared to existing methods.
Our results concern geometry of a manifold endowed with a pair of complementary orthogonal distributions (plane fields) and a time-dependent Riemannian metric. The work begins with formulae concerning deformations of geometric quantities as the Riemannian metric varies conformally along one of the distributions. Then w…
Paper tackles multi-label learning by improving SVR for positive semidefinite metrics.
problem Learning positive semidefinite metrics for multi-label and label distribution learning.
method Proposes two methods to overcome SVR's limitation in learning positive semidefinite metrics.
result Demonstrates new methods achieve favorable performance in multi-label and label distribution learning.
We consider three different approaches to define natural Riemannian metrics on polytopes of stochastic matrices. First, we define a natural class of stochastic maps between these polytopes and give a metric characterization of Chentsov type in terms of invariance with respect to these maps. Second, we consider the Fish…
Formula for scalar curvature under metric collapse.
problem Finding positive scalar curvature metrics.
method Formula involving scalar curvature and adapted orthonormal frame.
result Effect of metric collapse on scalar curvature.
Study curvature of piecewise metrics using moving frames.
problem Deriving a curvature measure for piecewise-smooth Riemannian metrics.
method Used moving frame techniques to derive curvature, showing it satisfies Cartan structure equations and gauge transformation law.
result Equivalence of the derived curvature to existing densitized distributional curvature.
New method for reducing dimensions of distributional data.
problem Nonlinear sufficient dimension reduction for distribution-on-distribution regression.
method Building universal kernels on metric spaces to characterize conditional independence.
result Method outperforms competing methods in synthetic and real data applications.
We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…
We say that a distribution is harmonic if it is harmonic when considered as a section of a Grassmann bundle. We find new examples of harmonic distributions and show nonexistense of harmonic distrubutions on some Riemannian manifolds by two different approaches. Firstly, we lift distributions to the second tangent bundl…
Modified Wasserstein metric for Gaussian distributions, invariant to isometries.
problem Distance measurement for latent Gaussian distributions invariant to isometries.
method Modified Benamou-Brenier approach leading to a Procrustes Wasserstein metric.
result For Gaussian distributions, the metric reduces to Euclidean distance between eigenvalues.
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.
Eisenhart's theorem extended to sub-Riemannian metrics on specific Lie algebras.
problem Extending Eisenhart's theorem to sub-Riemannian metrics on step 2 distributions.
method Introducing ad-surjective step 2 nilpotent Lie algebras and extending Eisenhart's theorem.
result The theorem holds for sub-Riemannian metrics on ad-surjective step 2 distributions.
We develop a comprehensive geometric framework for defining spaces of nonlinear generalized sections of vector bundles containing spaces of distributional sections . Our theory incorporates classical differential geometric operations (like tensor products, covariant deri…
Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There?stat.ML
The paper explores fairness metrics in automated decision-making and their limitations.
problem Discrimination in automated resource allocation decisions.
method Analysis of fairness metrics and distributive justice principles.
result Prominent fairness metrics fail to address egalitarian and sufficiency concerns in resource allocation.
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.
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…
Metric learning enhances combinatorial coverage metrics' ability to predict classification errors.
problem Dataset dependence of combinatorial coverage metrics in anticipating classification errors.
method Metric learning to improve latent space separation of data classes.
result Metric learning increases SDCCMs' ability to distinguish between correctly and incorrectly classified data.
UDJ-FL framework achieves multiple distributive justice-based fairness metrics in federated learning.
problem Ensuring fairness in federated learning across different client data distributions.
method UDJ-FL framework uses aleatoric uncertainty-based client weighing and fair resource allocation techniques.
result UDJ-FL achieves egalitarian, utilitarian, Rawls' difference principle, and desert-based fairness metrics.
Integral formulas for a metric-affine manifold with two complementary orthogonal distributionsmath.DG
We obtain integral formulas for a metric-affine space equipped with two complementary orthogonal distributions. The integrand depends on the Ricci and mixed scalar curvatures and invariants of the second fundamental forms and integrability tensors of the distributions. The formulas under some conditions yield splitting…
Quantum-inspired probability metrics define a complete, universal space for statistical learningstat.ML
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.
Paper optimizes classification of distributions using Wasserstein metric.
problem Classifying instances represented by distributions on a vector space.
method Maximizing Fisher's ratio in the Wasserstein metric space through iterative algorithm.
result The method enhances classification performance and is robust to variations in distribution summaries.
H. Weyl in 1921 demonstrated that for a connected manifold of dimension greater than , if two Riemannian metrics are conformal and have the same geodesics up to a reparametrization, then one metric is a constant scaling of the other one. In the present paper, we investigate the analogous property for sub-Riemannian …
The authors found extremals of arbitrary left-invariant sub-Finsler metric on the Engel group defined by a distribution of rank two. They use for this the Pontryagin Maximum Principle for the corresponding time-optimal problem in coordinates of the first kind. The obtained results are applied to the case of left-invari…
We propose a novel approach for comparing distributions whose supports do not necessarily lie on the same metric space. Unlike Gromov-Wasserstein (GW) distance which compares pairwise distances of elements from each distribution, we consider a method allowing to embed the metric measure spaces in a common Euclidean spa…
We investigate the geometrical structure of probabilistic generative dimensionality reduction models using the tools of Riemannian geometry. We explicitly define a distribution over the natural metric given by the models. We provide the necessary algorithms to compute expected metric tensors where the distribution over…
A new probabilistic approach improves deep metric learning by considering image uncertainties and class-specific variances.
problem Proxy-based deep metric learning struggles with image uncertainties and class-specific structures.
method Introduces non-isotropic probabilistic proxy-based deep metric learning using directional von Mises-Fisher distributions.
result Improves generalization performance and competitive on standard benchmarks.