Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things. We investigate …
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Vector Space Model”
Geometric Invariant Theory applied to Kähler manifolds yields analytic models for vector bundles.
problem Constructing local models for vector bundles on Kähler manifolds.
method Applying Geometric Invariant Theory to Kähler manifolds to construct analytic GIT-quotients.
result Existence of Weil-Petersson forms on parameter spaces for stable vector bundles.
The paper establishes concentration bounds for embeddings of generative models.
problem Analyzing statistical properties of generative models.
method High probability concentration bounds on sample vector embeddings using Data Kernel Perspective Space.
result Determines the number of samples needed for accurate approximation of generative model embeddings.
Model predicts travel time under rare conditions using a vector-space model.
problem Predicting travel time under rare temporal conditions (e.g., holidays, school vacations) is challenging due to limited historical data and other temporal changes.
method Presented a vector-space model for encoding rare temporal conditions, allowing coherent representation learning across different conditions.
result Increased performance for travel time prediction over different baselines when using the vector-space encoding for representing the temporal setting.
We give a method to construct stable vector bundles whose rank divides the degree over curves of genus bigger than one. The method complements the one given by Newstead. Finally, we make some systematic remarks and observations in connection with rationality of moduli spaces of stable vector bundles.
The paper analyzes user activities in OSNs using a vector space model.
problem Understanding user interactions and activity patterns in OSNs.
method TF-IDF scheme of Vector Space Model to analyze object-viewer relationships.
result Identified activity relationships among users and objects in OSNs.
Study the geometry and symmetries of moduli spaces of connections on KT manifolds.
problem Investigate the geometry and symmetries of moduli spaces of Hermitian-Einstein and instanton connections on KT manifolds.
method Analyze the geometry and symmetries of moduli spaces of Hermitian-Einstein and instanton connections on KT manifolds, using vector fields and connections with skew-symmetric torsion.
result The geometry of moduli spaces can be modeled on principal bundles with specific fibre and base spaces.
The present article provides a study of Killing vector fields on warped product manifolds as well as characterization of this structure on standard static and generalized Robertson-Walker space-times. Some conditions for a Killing vector field on a warped product manifold to be parallel are obtained. Moreover, …
SL(n) covariant valuations on Orlicz spaces are represented and characterized.
problem Representing SL(n) covariant valuations on Orlicz spaces.
method Representation theorem established for continuous, SL(n) covariant vector-valued valuations.
result Unique characterization of SL(n) covariant valuations as moment vectors.
Optimal transport for vector Gaussian mixtures improves efficiency and structure preservation.
problem Optimal mass transport for vector-valued Gaussian mixtures.
method Vectorizing Gaussian mixture models and studying optimal mass transport problems.
result Computational efficiency and structure preservation in optimal mass transport.
GCNNs on homogeneous spaces use vector bundles and Hilbert spaces.
problem Learning data on homogeneous spaces with global symmetry.
method Analysis of -equivariant convolutional layers on homogeneous spaces, using vector bundles and reproducing kernel Hilbert spaces.
result A precise criterion for expressing -equivariant layers as convolutional layers, leading to stronger results for some groups.
We introduce several techniques for sampling and visualizing the latent spaces of generative models. Replacing linear interpolation with spherical linear interpolation prevents diverging from a model's prior distribution and produces sharper samples. J-Diagrams and MINE grids are introduced as visualizations of manifol…
We prove the classification of the real vector subspaces of a quaternionic vector space by using a covariant functor which, to any pair formed of a quaternionic vector space and a real subspace, associates a coherent sheaf over the sphere.
We consider Killing vector fields on standard static space-times and obtain equations for a vector field on a standard static space-time to be Killing. We also provide a characterization of Killing vector fields on standard static space-times with compact Riemannian parts.
The paper studies Finsler spaces with semi-concurrent vector fields and their equivalence to Riemannian spaces.
problem Characterizing Finsler spaces with semi-concurrent vector fields.
method Analyzing various Finsler spaces and proving conditions for equivalence to Riemannian spaces.
result Various Finsler spaces (quasi--reducible, -like, -recurrent, -like) are equivalent to Riemannian spaces if they admit a semi-concurrent vector field.
The paper provides concentration bounds for embeddings of generative models.
problem Establishing accurate statistical analysis of generative models.
method Data Kernel Perspective Space embedding method.
result Required number of sample responses for accurate approximation.
Defines vector fields and differential forms on local C-infinity-ringed spaces.
problem No specific problem stated; focuses on mathematical definitions.
method Defines tangent sheaf, contractions, Lie derivatives, and proves Cartan equations.
result Standard Cartan calculus equations hold for local C-infinity-ringed spaces.
End-to-end graph SVM with graph convolutions and RKHS.
problem Graph classification with complex feature spaces.
method End-to-end training of graph convolutions, kernel function, and SVM parameters.
result Outperforms existing deep learning models on graph classification tasks.
New pushforward operation on vector pseudo-bundles creates new examples.
problem Creating new objects from vector bundle theory in diffeology.
method Introducing pushforward operation on diffeological vector pseudo-bundles.
result Pushforward operation produces new projective diffeological vector spaces.
We propose an algorithm for exploring the entire regularization path of asymmetric-cost linear support vector machines. Empirical evidence suggests the predictive power of support vector machines depends on the regularization parameters of the training algorithms. The algorithms exploring the entire regularization path…
Constructs a representation of the string 2-group on a von Neumann algebra.
problem Establishing a categorified spinor representation of the string 2-group.
method Using the Morita bicategory of von Neumann algebras, specifically the hyperfinite type III_1 factor.
result Demonstrates a categorification of the spinor representation.
The study classifies spaces with specific conformal vector fields.
problem Characterizing closed vacuum static spaces with non-Killing conformal vector fields.
method Provided characterizations and established an identity involving the characteristic function.
result Derived a rigidity theorem and classified spaces with the vector field.
Study of differential forms and vector fields on orbit spaces.
problem Understanding vector fields and differential forms on orbit spaces.
method Defined differential forms and vector fields as multilinear maps on infinitesimal diffeomorphisms.
result Intrinsic view of vector fields and differential forms on orbit spaces.
In this paper we consider the complex vector spaces of holomorphic cross-sections of homogeneous holomorphic vector bundles over elliptic adjoint orbits, and provide a sufficient condition for the vector spaces to be finite dimensional in view of root systems.
The paper introduces novel Gaussian process models for vector-valued signals on manifolds.
problem Modeling vector-valued signals on non-Euclidean domains, especially for applications like wind speeds.
method Intrinsically defined Gaussian vector fields on manifolds, accounting for manifold geometry.
result Gaussian vector fields provide more refined inductive biases than extrinsic fields.
Steerable neural ODEs on homogeneous spaces for equivariant feature dynamics.
problem Learning continuous-time equivariant dynamics of vector-valued features on homogeneous spaces.
method Introduces steerable neural ordinary differential equations on homogeneous spaces, interpreting features as sections of associated vector bundles over .
result Steerable NODEs are -equivariant when the flow and connection are -invariant, and they incorporate existing models.
An Algorithm to perform Covariance-Adjusted Support Vector Classification in Non-Euclidean Spacescs.LG
Algorithm improves SVM classification in non-Euclidean spaces.
problem Limitations of traditional SVM in non-Euclidean spaces.
method Covariance-adjusted SVM using Cholesky Decomposition.
result Cholesky-SVM outperforms traditional SVM in non-Euclidean spaces.
We give a representation of canonical vector bundles over Grassmannian manifolds as non-compact affine symmetric spaces as well as their Cartan model in the group of the Euclidean motions.
Paper introduces stratified vector bundles and their properties.
problem Understanding singular spaces and their vector bundles.
method Characterization via monoid actions and examples from various fields.
result Functorial properties extended to the stratified case.
Study projective symmetries in Finsler spaces, showing reductions and constant flag curvature.
problem Exploring projective symmetries in Finsler spaces and their properties.
method Analyzing algebraic sub-algebras and curvature invariants of projective vector fields.
result Closed Finsler spaces with negative Ricci curvature reduce to Killing vector fields.
We prove implicit function theorems for mappings on topological vector spaces over valued fields. In the real and complex cases, we obtain implicit function theorems for mappings from arbitrary (not necessarily locally convex) topological vector spaces to Banach spaces.
Defines quaternionic k-vector fields on quaternionic Kähler manifolds.
problem No specific problem stated; focuses on definition and properties.
method Introduced a modified Dirac operator to define quaternionic k-vector fields.
result Calculated the dimension of quaternionic k-vector fields on .
This work describes compactifications of metric spaces and vector spaces using asymmetric norms.
problem Compactifying metric spaces and vector spaces using asymmetric norms.
method Nonstandard methods, ultrapowers of the spaces at hand.
result Polyhedral compactifications of vector spaces with stratified structure.
Study Kähler geometry on vector bundles over elliptic curves.
problem Characterize Kähler metrics on vector bundle total spaces.
method Analyzing function theory and Kähler geometry on vector bundles of degree zero.
result Biholomorphic total spaces correspond to isomorphic vector bundles.
The paper proves non-existence of torqued and anti-torqued vector fields on hyperbolic spaces.
problem Existence of torqued and anti-torqued vector fields on hyperbolic spaces.
method Analyzing the properties of conformal scalar functions and their impact on the existence of vector fields.
result Non-existence of proper torqued and anti-torqued vector fields on hyperbolic spaces.
Finite spaces can be or not coproducts of subspaces.
problem When finite-dimensional diffeological vector spaces are coproducts of their subspaces.
method Reviewing the question in diffeological vector spaces and comparing with other categories.
result Finite-dimensional spaces can be coproducts, but not always.
New method reduces word embedding storage space by 100x.
problem Large space required for storing word embeddings.
method Inspired by quantum computing, proposes word2ket and word2ketXS methods.
result Achieves a hundred-fold reduction in space required for word embeddings.
A study of proper affine vector fields in plane symmetric static space-times by using the rank of the Rieman matrix and holonomy. Studying proper affine vector fields in each case, It is shown that the special class of the above space-times admit proper affine vector fields.
We present Vector-Space Markov Random Fields (VS-MRFs), a novel class of undirected graphical models where each variable can belong to an arbitrary vector space. VS-MRFs generalize a recent line of work on scalar-valued, uni-parameter exponential family and mixed graphical models, thereby greatly broadening the class o…
New differential geometry perspective on orthogonal RNNs.
problem Mitigating exploding and vanishing gradients in RNNs.
method Using tools from differential geometry, parameterizing vector fields via directional derivatives of scalar functions.
result Our approach achieves comparable or better results on benchmark tasks.
This study's goal is to create a model of sentiment analysis on a 2000 rows IMDB movie comments and 3200 Twitter data by using machine learning and vector space techniques; positive or negative preliminary information about the text is to provide. In the study, a vector space was created in the KNIME Analytics platform…
Study Ricci vector fields on 2D space with diagonal metrics.
problem Understanding Ricci vector fields on 2D space with specific metrics.
method Examined Ricci vector fields on with a diagonal metric.
result Characterized Ricci vector fields on with a diagonal metric.
Maps vector fields between stacks and orbit spaces.
problem Understanding vector fields on stacks and orbit spaces.
method Morita stratifications and geometric vector fields correspondence.
result Derives stacky version of Gauss lemma and extends Palais' theorem.
Novel metric space magnitude and weighting vectors improve machine learning tasks.
problem Improving machine learning algorithms using novel metric space concepts.
method Metric space magnitude and weighting vectors for better machine learning.
result The weighting vector effectively detects boundaries and improves classic machine learning tasks.
In this paper, we study geodesics and geodesic vectors for homogeneous exponential Finsler space and homogeneous infinite series Finsler space. Further, we find necessary and sufficient condition for a non-zero vector in these homogeneous spaces to be a geodesic vector.
We explore the potential of a popular distributional semantics vector space model, word2vec, for capturing meaningful relationships in ecological (complex polyphonic) music. More precisely, the skip-gram version of word2vec is used to model slices of music from a large corpus spanning eight musical genres. In this newl…
New method for mesh denoising using TGV of normal vector field.
problem Improving mesh quality by removing noise.
method Proposes a novel TGV formulation for normal vector fields on triangular meshes.
result New method outperforms existing techniques in mesh denoising experiments.
Develops vector-valued RKBS for neural networks and operators.
problem Understanding function spaces of -valued neural networks and neural operators.
method Defines and constructs vector-valued RKBS (vv-RKBS) without restrictive assumptions.
result Establishes Representer Theorem for neural architectures.