Algorithm learns latent simplex from perturbed points in input-sparsity time.
problem Learning a latent k-vertex simplex from noisy data. method Input-sparsity time algorithm using low-rank approximation and adaptive selection.
result Algorithm achieves O(extrmnnz(A)) time complexity, avoiding k⋅extrmnnz(A). A new model integrates covariates with grade of membership analysis for better latent structure recovery.
problem Improving latent structure recovery in multivariate categorical data analysis.
method Covariate-assisted grade of membership model exploiting shared low-rank simplex geometry.
result Auxiliary covariates can provably improve latent structure recovery, leading to faster convergence rates.
Study classifies submanifolds in probability simplex.
problem Classifying submanifolds in the probability simplex.
method Complete classification through geometric analysis.
result Doubly totally-umbilical submanifolds identified and classified.
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.
On the probability simplex, we can consider the standard information geometric structure with the e- and m-affine connections mutually dual with respect to the Fisher metric. The geometry naturally defines submanifolds simultaneously autoparallel for the both affine connections, which we call {\em doubly autoparallel s…
Introduces a new geometric framework for probability distributions.
problem Developing a geometric framework for probability distributions.
method Introduces ℓp-information geometry and defines the ℓ2-probability simplex via the q-root transform. result Defines a noncanonical differentiable structure and q-root map as an isometry. Geometry-aware KDE model improves multiclass quantification.
problem Accurately estimating class prevalence for label shift adaptation.
method Log-ratio representations and Aitchison geometry for compositional data, shrinkage regularization.
result Competitive with state-of-the-art quantifiers, often improving over standard KDE-based baselines.
This work generalizes a geometric Laplacian determinant description to higher dimensions.
problem Defining and understanding the Laplacian determinant in higher dimensions with non-Delaunay triangulations.
method Geometric description of the Laplacian determinant in higher dimensions, relating it to volume quantities derived from simplex geometry.
result Generalizes geometric Laplacian determinant description to higher dimensions, showing negative semidefiniteness and kernel of constants.
In the probabilistic topic models, the quantity of interest---a low-rank matrix consisting of topic vectors---is hidden in the text corpus matrix, masked by noise, and the Singular Value Decomposition (SVD) is a potentially useful tool for learning such a low-rank matrix. However, the connection between this low-rank m…
New compression methods handle biased input sequences for more accurate posterior summaries.
problem Handling biased input sequences for accurate posterior summaries.
method Stein kernel thinning, low-rank SKT, Stein recombination, Stein Cholesky.
result Achieves accurate posterior summaries with biased input sequences.
The Apollonius theorem is generalized for m-simplices, with applications in geometry and optimization.
problem Generalizing the Apollonius theorem for m-simplices.
method Direct generalization of the theorem to m-simplices in n-dimensional space.
result Applications in geometry and optimization, including minimal surface enclosures, simplex thickness, and root-finding methods.
Proposes a new matrix factorization model for interval-valued matrices.
problem Matrix factorization for matrices with entries in a given interval.
method Bounded simplex-structured matrix factorization (BSSMF) with fast algorithm for missing data.
result BSSMF provides a unique decomposition under certain conditions.
Study shows neural collapse is invariant to class imbalances under certain conditions.
problem Neural collapse properties are only valid for balanced data.
method Adopted UFM and introduced SELI for invariant characterization.
result Embeddings and classifiers always interpolate a simplex-encoded label matrix regardless of class imbalances.
High dimensional data often contain multiple facets, and several clustering patterns can co-exist under different variable subspaces, also known as the views. While multi-view clustering algorithms were proposed, the uncertainty quantification remains difficult --- a particular challenge is in the high complexity of es…
We propose Dirichlet Simplex Nest, a class of probabilistic models suitable for a variety of data types, and develop fast and provably accurate inference algorithms by accounting for the model's convex geometry and low dimensional simplicial structure. By exploiting the connection to Voronoi tessellation and properties…
A function is exponentially concave if its exponential is concave. We consider exponentially concave functions on the unit simplex. In a previous paper we showed that gradient maps of exponentially concave functions provide solutions to a Monge-Kantorovich optimal transport problem and give a better gradient approximat…
Neural networks exhibit simplex symmetry in their final and penultimate layers.
problem Understanding the symmetry in neural network layers.
method Analytical and numerical studies of toy models and deep neural networks.
result Neural networks map data points from the same class to a single point in a high-dimensional space, forming a simplex.
We study a natural intrinsic definition of geometric simplices in Riemannian manifolds of arbitrary dimension n, and exploit these simplices to obtain criteria for triangulating compact Riemannian manifolds. These geometric simplices are defined using Karcher means. Given a finite set of vertices in a convex set on t…
Researchers correct earlier work on surgeries of Gieseking's hyperbolic simplex manifold.
problem Incorrectly identified Gieseking's manifold as orbifolds, leading to a conflict with known theorems.
method Revised and completed the analysis of Dehn surgeries on Gieseking's manifold, identifying them as cone manifolds.
result Corrected the understanding of Gieseking's manifold, identifying it as cone manifolds and derived new orbifold series.
It is shown that the Hilbert geometry (D,hD) associated to a bounded convex domain D⊂En is isometric to a normed vector space (V,∣∣⋅∣∣) if and only if D is an open n-simplex. One further result on the asymptotic geometry of Hilbert's metric is obtained with corollaries for the behavior …
CoreFlow models matrix-valued distributions efficiently, preserving shared low-rank structure.
problem Learning matrix-valued distributions from high-dimensional and incomplete data.
method Low-rank flow model that learns shared row/column subspaces and trains a normalizing flow on the core.
result CoreFlow improves generation quality in few-sample regimes and remains competitive in data-rich settings.
We introduce a new distance metric for non-linear embeddings of Tempered Exponential Measures.
problem Non-linear embeddings of Tempered Exponential Measures (TEMs).
method Parameterization of finite discrete TEMs via Legendre functions, introducing tempered Hilbert co-simplex distance.
result Established a generalization of the Hilbert log cross-ratio simplex distance to a tempered Hilbert co-simplex distance.
A new method normalizes flow mixtures for better inference across different data types.
problem Inference failure across diverse posterior geometries in normalizing flows.
method Introduces a two-stage framework with a stable global weighting mechanism based on sEMA.
result Achieves consistent NLL improvements and stable weight trajectories over baselines.
PolyILR: A Tree-Structured Orthonormal Decomposition of Compositional Data
problem Representing compositional data with hierarchical structure
method PolyILR: A canonical orthonormal decomposition of the Aitchison tangent space aligned with any tree topology
result PolyILR yields stable, interpretable features and enables inference at multiscale tree resolution
The paper triangulates Heisenberg groups with horizontal and straight simplexes.
problem Triangulating Heisenberg groups with specific regularity properties.
method Constructing triangulations with horizontal and straight simplexes on a polyhedral structure and extending to the whole Heisenberg group.
result Explicit examples of grid and triangulations provided.
A theory of cellwise contamination for compositional data using log-ratios.
problem Contamination in compositional data analysis.
method Develops a theory combining contamination model and propagation theorem.
result Reduction in cellwise breakdown value by (D−1)/D for certain estimators. Study the distribution for low-rank matrix learning, improving inference methods.
problem Lack of understanding of underlying probability distributions in low-rank matrix learning.
method Analyze the distribution f(X)∝e−λ∥X∥∗, using differential geometry to design an improved MCMC algorithm and learn penalty parameter λ. result Improved MCMC algorithm and penalty parameter learning for low-rank Bayesian inference.
A new geometry-preserving method for interpreting compositional data.
problem Statistical challenges in high-dimensional compositional data.
method Geometry-preserving framework for dimension reduction of compositional data.
result Identification of a central compositional subspace for compositional predictors.
In the context of Synthetic Differential Geometry, we describe the square volume of a ``second-infinitesimal simplex'', in terms of square-distance between its vertices. The square-volume function thus described is symmetric in the vertices. The square-volume gives rise to a characterization of the volume form in the t…
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.
Study optimal transport on simplex boundary, proving transport map and potential regularity.
problem Regularity of transport map and potential on simplex boundary.
method Boundary regularity results for optimal transport maps, exploiting simplex symmetries.
result Regularity properties of transport map and its convex potential.
Introduces new geometric framework for probability densities on manifolds.
problem Developing a new geometric framework for probability densities on manifolds.
method Introduces ℓp-information geometry and defines ℓ2-probability simplex with q-root transform. result Explicit solution of gradient flow and geodesic completeness of e-connection. We propose that a simple, Lagrangian 2d N=(0,2) duality interface between the 3d N=2 XYZ model and 3d N=2 SQED can be associated to the simplest triangulated 4-manifold: the 4-simplex. We then begin to flesh out a dictionary between more general triangulated 4-manifolds with boundar…
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…
A correspondence between three-dimensional flat connections and constant curvature four-dimensional simplices is used to give a novel quantization of geometry via complex SL(2,C) Chern-Simons theory. The resulting quantum geometrical states are hence represented by the 3d blocks of analytically continued Chern-Simons t…
Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity in embedding space is not optimized in the learning. In this paper we propose a …
The Bezier simplex fitting is a novel data modeling technique which exploits geometric structures of data to approximate the Pareto front of multi-objective optimization problems. There are two fitting methods based on different sampling strategies. The inductive skeleton fitting employs a stratified subsampling from e…
PRISM identifies simplex vertices from noisy data.
problem Identifying vertices of a simplex from noisy data.
method Probabilistic simplex model with maximum likelihood inference.
result Vertices are identifiable under certain assumptions.
A new optimization method for probability simplex problems.
problem Optimizing convex problems over the probability simplex.
method Cauchy-Simplex iteration scheme, mapping to sphere, gradient descent, and back-mapping.
result Convergence results and faster convergence in high dimensions.
We establish the second part of Milnor's conjecture on the volume of simplexes in hyperbolic and spherical spaces. A characterization of the closure of the space of the angle Gram matrices of simplexes is also obtained.
Proposes a new method for multi-class classification with well-calibrated predictions.
problem Improving the accuracy and reliability of multi-class classification models.
method Trains data in a latent space induced by an (n−1)-dimensional simplex, then extends and fits a regression model. result Demonstrates a well-calibrated classifier with improved prediction and calibration properties.
This work investigates implicit bias in multiclass separable data using a novel geometry-aware optimizer.
problem Understanding implicit bias in overparameterized models on multiclass separable data.
method Introduces NucGD, a geometry-aware optimizer enforcing low-rank structures through nuclear norm constraints.
result NucGD enables scalable training and characterizes the impact of stochastic optimization dynamics.
Derives smooth homogeneous structures for low-rank tensors.
problem Understanding the geometry of low-rank tensors.
method Analyzes sets of fixed CP, multilinear, and TT rank tensors to derive smooth homogeneous manifolds.
result Derives Riemannian metrics with complete geodesics.
Paper finds sample complexity for learning high-dimensional simplices from noisy data.
problem Learning high-dimensional simplices from noisy samples.
method Combines sample compression, high-dimensional geometry, and Fourier analysis.
result Proves sample complexity bound for achieving a simplex within a certain distance from the true simplex.
A hyperbolic 3-simplex reflection group is a Coxeter group arising as a lattice in the isometry group of hyperbolic 3-space, with fundamental domain a geodesic simplex (possibly with some ideal vertices). The classification of these groups is known, and there are exactly 9 cocompact examples, and 23 non-cocompact examp…
We introduce the non-pure versions of simplicial balls and spheres with minimum number of vertices. These are a special type of non-homogeneous balls and spheres (NH-balls and NH-spheres) satisfying a minimality condition on the number of maximal simplices. The main result is that minimal NH-balls and NH-spheres are pr…
In 1973, J. Cheeger and J. Simons raised the following question that still remains open and is known as the Rational Simplex Problem: Given a geodesic simplex in the spherical 3-space so that all of its interior dihedral angles are rational multiples of π, is it true that its volume is a rational multiple of the volu…
A new method for approximating softmax and Gaussian kernels with reduced error.
problem Approximating softmax and Gaussian kernels with low error.
method Simplex Random Features (SimRFs) and SimRFs+.
result SimRFs provide the smallest MSE among weight-independent geometrically-coupled PRF mechanisms.