Proposes a new latent variable model for hyperspherical latent spaces.
problem Efficiently modeling heavy-tailed distributions in hyperspherical latent spaces.
method Introduces spherical Cauchy (spCauchy) latent variables and applies Möbius transformations.
result Shows spCauchy recovers vMF geometry in high-concentration limits and avoids complex evaluations.
SAE improves VAE's latent space precision in high dimensions.
problem High-dimensional latent codes vs probabilistic inference in VAEs.
method Spherical Auto-Encoder (SAE) with spherical normalization on latent space.
result SAE improves latent code inference precision in high dimensions.
New autoencoder improves latent space learning by optimizing sliced Gromov-Wasserstein discrepancies.
problem Improving inner discrepancy between prior and posterior distributions in autoencoders.
method Proposed spherical sliced fused Gromov Wasserstein (SSFG) and variants (MSSFG, PSSFG) to find important directions.
result New autoencoders achieve favorable performance in latent manifold learning, image generation, and reconstruction.
Generative Latent Implicit Conditional Optimization (GLICO) learns from small samples.
problem Learning from small labeled datasets.
method Generative Latent Implicit Conditional Optimization (GLICO) learns a latent space and generator from small labeled data.
result GLICO synthesizes new samples for every class using as few as 10 examples per class.
Corrected whitening restores orthogonality in high-dimensional spherical Gaussian mixtures.
problem In high-dimensional data, standard whitening fails to preserve orthogonality of mixture means.
method Derived exact limits for whitened means dot products using random matrix theory, constructed a corrected whitening matrix.
result Corrected whitening allows for improved estimation of spherical Gaussian mixtures in the large-dimensional regime.
A new distribution addresses scalability and numerical stability issues of the vMF.
problem Scalability and numerical stability issues in sampling from the von Mises-Fisher (vMF) distribution.
method Proposes the Power Spherical distribution, retaining vMF's properties but addressing its drawbacks.
result Demonstrates the stability of Power Spherical distributions and applies it to a variational auto-encoder.
New spectral clustering method for graphs with uneven node degrees.
problem Challenges in community detection for graphs with heterogeneous degree distributions.
method Spectral clustering on spherical coordinates with degree correction.
result Improved performance in representing computer networks.
Bayesian models for networks are often misspecified, leading to overconfident inference.
problem Real-world networks violate assumptions of geometry and link function in latent space models.
method Proposes a generalized posterior framework for random geometric graphs, using Link-Sequential R-SafeBayes to adaptively tune posterior regularization.
result Improved calibration and better link prediction performance demonstrated on synthetic and real-world networks.
AMES framework selects optimal embedding space for latent graph inference.
problem No principled method for choosing the best embedding space for latent graph inference.
method Differentiable AMES framework using backpropagation to select optimal embedding space.
result Consistently achieves comparable or superior results across multiple datasets.
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…
Researchers prove inner product recovery is impossible in latent space models.
problem Recovering inner products in latent space models with random geometric graphs.
method Rate-distortion theory applied to Gaussian or spherical latent locations.
result Impossible to recover inner products if dimensionality exceeds nh(p), matching positive results' conditions. NLGS optimizes latent geometry for better model performance.
problem Improving machine learning model performance by aligning latent space geometry with data structure.
method NLGS uses product manifolds with Gromov-Hausdorff distance for latent geometry search.
result NLGS finds optimal latent geometry with query-efficient Bayesian optimization.
New tests for identifying the number of latent factors in short panels with small time dimensions.
problem Determining the number of latent factors in short panels with small time dimensions.
method Eigenvalue tests based on variance-covariance matrices of asset returns, with assumptions on spherical errors or instrumental variables for factor betas.
result Established asymptotic distributional results and proposed a novel statistical test for weak factors.
Method for factor analysis in short panels without assuming sphericity or Gaussianity.
problem Factor analysis in short panels without assuming sphericity or Gaussianity.
method Pseudo maximum likelihood method and asymptotically uniformly most powerful invariant test.
result Systematic risk explains a large part of cross-sectional total variance in bear markets but is not spanned by observed factors.
We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical Gaussian mixtures, ICA, and sparse coding models. We provide tight concentration…
This work proposes a novel approach to learn quantizers from data, improving similarity search performance.
problem Learning optimal quantizers for multi-dimensional data distributions.
method Train a neural net to form a fixed parameter-free quantizer, using uniformity in a spherical latent space as a proxy objective.
result The proposed method outperforms most learned quantization methods and is competitive with state-of-the-art approaches.
New findings show fundamental group is not audible in spherical space forms.
problem Isospectral spherical space forms with non-cyclic fundamental groups.
method Revisited and found new examples of spherical space forms.
result Fundamental group is not audible among spherical space forms.
New curvature positivity helps classify spherical spaces and complex projective spaces.
problem Classifying spherical space forms and complex projective spaces.
method Introducing a new positivity notion for curvature.
result Characterizations for spherical space forms and complex projective spaces.
Proposes a new approach to enforce uniform distribution on torus.
problem Enforcing uniform distribution on torus for generative models.
method Introduces circular spring loss to enforce equally spaced points on torus.
result Enables morphing between points on torus with different paths.
Paper explores neural network approximations on sphere domains.
problem Approximating functionals on sphere domains using neural networks.
method Encoder-decoder framework with spherical harmonics for infinite-dimensional domain.
result Approximation rates of neural networks with different encoder structures.
Statistical models with constrained probability distributions are abundant in machine learning. Some examples include regression models with norm constraints (e.g., Lasso), probit, many copula models, and latent Dirichlet allocation (LDA). Bayesian inference involving probability distributions confined to constrained d…
Minimal surfaces in spherical space forms have limited genus.
problem Understanding minimal surfaces in spherical space forms.
method Analyzing orientable index one minimal surfaces with large fundamental groups.
result Surfaces have genus at most two, confirming a conjecture.
In this paper we consider the spherical slant helices in R3. More- over, we show how could be obtained to a spherical slant helix and we give some spherical slant helix examples in Euclidean 3-space.
Study spherical surfaces with conical points, proving systole inequality.
problem Characterize moduli spaces of spherical metrics with conical singularities.
method Analyze systole inequality and properness of forgetful map.
result Explicit systole inequality linking metric and conformal invariants.
Researchers find highest volumes for isospectral spherical orbifolds and space forms.
problem Finding the maximum volumes of isospectral spherical orbifolds and space forms.
method Analyzing isospectral properties and calculating volumes of spherical orbifolds and space forms.
result Highest volumes for specific dimensions and conditions of isospectral spherical orbifolds and space forms.
In this work, we studied the properties of the spherical indicatrices of involute curve of a space curve and presented some characteristic properties in the cases that involute curve and evolute curve are slant helices and helices, spherical indicatrices are slant helices and helices and we introduced new representatio…
Study on metrics with positive scalar curvature on spherical space forms.
problem Determining metrics with positive scalar curvature on spherical space forms.
method Analysis of moduli spaces of metrics with positive scalar curvature on topological spherical space forms.
result Determination of the number of path components of moduli spaces for dimensions at least 5 and non-simply connected forms.
Develops efficient algorithms for learning latent-variable models using implicit moment tensor computation.
problem Learning latent-variable models with moment tensors of super-constant degree.
method Implicit moment tensor computation for general models, extending previous work on clustering mixtures of spherical Gaussians.
result First poly(d, k) time learning algorithms for various models including mixtures of linear regressions, spherical Gaussians, and positive linear combinations of non-linear activations.
In this paper, we give definitions and characterizations of normal and spherical curves in the dual space. We show that normal curves are also spherical curves in D^3.
The paper explores integral formulas and behavior of spherical functions.
problem None explicitly stated, focuses on spherical functions.
method Integral formulas and behavior analysis at infinity.
result New integral formulas and results about behavior at infinity.
Study spherical images of modified vector fields on a unit sphere.
problem Understanding spherical images of modified vector fields.
method Analysis of spherical images using modified orthogonal vector fields and Darboux vector.
result Characterization of spherical indicatrices with modified orthogonal frame.
In the present study we consider the generalized rotational surfaces in Euclidean spaces. Firstly, we consider generalized spherical curves in Euclidean (n+1)−space En+1. Further, we introduce some kind of generalized spherical surfaces in Euclidean spaces E3 and respect…
DELIMIT PyTorch enhances deep learning for diffusion imaging.
problem Applying deep learning to spherical diffusion imaging data.
method Added spherical harmonic interpolation and local convolution layers to PyTorch.
result Deep learning can now be applied conveniently to diffusion imaging data.
Simple Deep LDA models achieve accuracy competitive with softmax baselines.
problem Training Deep LDA models by maximum likelihood estimation leads to overlapping or collapsed class clusters.
method Proposed a constrained Deep LDA formulation with geometric constraints to fix class means and covariance.
result MLE becomes stable under geometric constraints, yielding well-separated class clusters.
Timelike geometry of spherical simplices is shown to be isometric to vector spaces.
problem Characterizing the geometry of spherical simplices.
method Proved isometry to vector spaces with a timelike norm.
result Timelike spherical Hilbert geometry of simplices is isometric to a union of six copies of vector spaces.
VJE learns latent representations without contrastive learning, providing probabilistic semantics.
problem Learning latent representations without contrastive signals.
method VJE maximizes a symmetric conditional evidence lower bound (ELBO) on paired encoder embeddings, using a Student-t distribution on a polar representation.
result VJE outperforms standard non-contrastive baselines in ImageNet-1K, CIFAR-10/100, and STL-10.
The paper proves stability of inequalities for nearly spherical sets in various spaces.
problem Stability of geometric inequalities for nearly spherical sets.
method Deriving a quantitative quermassintegral inequality and applying it to derive stability results.
result Stability of geometric inequalities involving weighted curvature integrals and quermassintegrals for nearly spherical sets in Rn+1 and Hn+1. Study local features of decorated representation spaces for spherical surfaces.
problem Local structure of moduli space of spherical surfaces with conical points.
method Analysis of decorated representation spaces of fundamental groups in SU(2).
result Smooth locus of decorated representation spaces is dense and connected.
Study spherical convex bodies using Lp-floating areas and curvature entropy.
problem Analogous isoperimetric inequalities for spherical convex bodies.
method Introduced Lp-floating areas and curvature entropy for spherical convex bodies. result Established isoperimetric inequalities and dual isoperimetric inequalities.
This paper is the second part of a study of the quantum free particle on spherical and hyperbolic spaces by making use of a curvature-dependent formalism. Here we study the analogues, on the three-dimensional spherical and hyperbolic spaces, $S_\k^3$ (κ>0) and $H_\k^3$ (κ<0), to the standard {\itshape spherical wav…
Estimates latent norms and Gram matrices for graphs on Euclidean balls.
problem Estimating latent points and their relationships in graphs on Euclidean balls.
method Estimates latent norms and Gram matrices using observed graph data.
result Graphs on Euclidean balls can have power-law degree distributions.
Locally classifies 4D spherical symmetric Finsler spaces.
problem Classifying 4D spherical symmetric Finsler spaces.
method Local classification of pseudo-Finsler Berwald structures.
result Six classes of non-Riemannian SO(3)-symmetric pseudo-Finsler Berwald functions.
Study null surfaces of pseudo-spherical curves in anti-de Sitter space.
problem Characterize null surfaces of pseudo-spherical spacelike framed curves in anti-de Sitter 3-space.
method Introduced nullcone fronts, classified singularities, defined Anti-de Sitter distance-squared functions.
result Relate singularities of nullcone fronts to those of framed curves.
Study calculates eigenvalues and eigenfunctions for spherical triangles and finds fundamental gap behavior.
problem Understanding eigenvalues and gaps in spherical triangles.
method Explicit computation of Dirichlet eigenvalues and eigenfunctions for spherical lunes and triangles.
result Fundamental gap of spherical triangles increases as the angle of the lune decreases.
String-net models explore non-spherical fusion categories, revealing new spin structures and representations.
problem Investigating string-net models in non-spherical fusion categories.
method String-net models associate vector spaces to surfaces in terms of graphs decorated by objects and morphisms of a pivotal fusion category.
result String-net spaces count r-spin structures and carry representations of the mapping class group.
Study spectral properties of sparse random graphs to recover latent vectors.
problem Recovering latent vectors in sparse random geometric graphs.
method Analyzes spectral concentration and uses orthogonal polynomial expansions, decoupling, and matrix concentration.
result Sharpens spectral norm bounds and proves exact recovery for Gaussian mixture models.
A new distance metric for vMF distributions simplifies spherical data analysis.
problem Intractability of normalization constants and lack of suitable geometric metrics for comparing vMF distributions.
method Proposes a Wasserstein-like distance that decomposes vMF distribution discrepancies into angular and concentration components.
result The proposed distance metric induces a latent geometric structure on the space of non-degenerate vMF distributions.
We prove that spherical spectral analysis and synthesis hold in Damek-Ricci spaces and derive two-radius theorems.