Paper proposes a new covariance estimator ensuring positive semi-definite matrices.
problem Estimating spot covariance matrices while maintaining positive semi-definiteness.
method Modification of the Fourier covariance estimator with a symmetric positive semi-definite constraint.
result The estimator is consistent and produces accurate positive semi-definite matrices.
Paper develops Riemannian geometry for SPSD matrices with DA applications.
problem Riemannian geometry of SPSD matrices for DA.
method Closed-form expressions, approximations of geodesic path, PT, canonical representation.
result Proposes an algorithm for DA with improved performance.
New method for symmetric matrix completion using ReLU sampling.
problem Symmetric positive semi-definite low-rank matrix completion with deterministic entry-dependent sampling.
method ReLU sampling, gradient descent with tailored initialization.
result Gradient descent with tailored initialization achieves global minima.
Proves Gerber statistic is always non-negative.
problem Verifying the positive semi-definiteness of Gerber statistic.
method Analytical proof of both forms of Gerber statistic.
result Gerber statistic is positive semi-definite.
Fundamental weight systems identified as quantum states.
problem Identifying which weight systems are quantum states.
method Analyzing the Cayley distance kernel on the symmetric group and its positivity.
result All fundamental gl(n)-weight systems are quantum states.
As is well known, a metric on a manifold determines a unique symmetric connection for which the metric is parallel: the Levi-Civita connection. In this paper we investigate the inverse problem: to what extent is the metric of a Riemannian manifold determined by its Levi-Civita connection? It is shown that for a generic…
We propose two practical non-convex approaches for learning near-isometric, linear embeddings of finite sets of data points. Given a set of training points X, we consider the secant set S(X) that consists of all pairwise difference vectors of X, normalized to lie on the unit sphere. …
A new method for hierarchical clustering is presented. It combines treelets, a particular multiscale decomposition of data, with a projection on a reproducing kernel Hilbert space. The proposed approach, called kernel treelets (KT), effectively substitutes the correlation coefficient matrix used in treelets with a symm…
New approach to analyze matrix denoising using gradient flow and fixed point equations.
problem Positive semi-definite matrix denoising in extensive-rank and high-dimensional settings.
method Gradient flow and fixed point equations derived from linear pencil techniques of random matrix theory.
result Continuous phase transitions in the extensive-rank and high-dimensional regime.
The paper characterizes Einstein 4-manifolds with semi-definite curvature and derives inequalities.
problem Characterizing Einstein 4-manifolds with semi-definite sectional curvature.
method Using pointwise inequalities involving scalar curvature and Weyl curvatures.
result Closed 4-dimensional Einstein metrics saturating the pointwise inequality are completely characterized.
We propose a new input perturbation mechanism for publishing a covariance matrix to achieve (ε,0)-differential privacy. Our mechanism uses a Wishart distribution to generate matrix noise. In particular, We apply this mechanism to principal component analysis. Our mechanism is able to keep the positive semi-definitene…
In machine learning or statistics, it is often desirable to reduce the dimensionality of a sample of data points in a high dimensional space Rd. This paper introduces a dimensionality reduction method where the embedding coordinates are the eigenvectors of a positive semi-definite kernel obtained as the sol…
Determinantal point processes (DPPs) have attracted substantial attention as an elegant probabilistic model that captures the balance between quality and diversity within sets. DPPs are conventionally parameterized by a positive semi-definite kernel matrix, and this symmetric kernel encodes only repulsive interactions …
A new method for deep Wishart processes improves kernel-based models.
problem Inference in deep Wishart processes is challenging due to the need for flexible distributions over positive semi-definite matrices.
method Developed a novel approach to flexible distributions over positive semi-definite matrices using the Bartlett decomposition of the Wishart probability density. Used this to create an approximate posterior for the DWP.
result Improved performance of inference in the DWP compared to DGP with equivalent prior.
New geometric structures defined on SPD matrices for better understanding.
problem Understanding SPD matrices and their geometric properties.
method Introducing Finslerian and dual information-geometric structures on James' bicone domain.
result Geodesics correspond to straight lines in coordinate systems, and new dissimilarities generalize existing ones.
Introduce Collapsed Effective Operators for higher-order structures.
problem Existing spectral operators decompose topology into separate ranks, leaving practitioners to fuse information back to vertices.
method Introduce Collapsed Effective Operators via Schur complementation of a graded Laplacian.
result Preserves positive semi-definiteness, lowers system energy under higher-order connectivity.
Upper bound found for dimensions of subspaces where holomorphic sectional curvature vanishes.
problem Finding upper bounds for dimensions of subspaces where holomorphic sectional curvature vanishes.
method Connection with D'Angelo's work on complex subvarieties of real algebraic varieties and decomposition of polynomials into differences of squares.
result An upper bound for the dimensions of these subspaces is found.
In this paper we present a slight modification of the Fourier estimation method of the spot volatility (matrix) process of a continuous Itô semimartingale where the estimators are always non-negative definite. Since the estimators are factorized, computational cost will be saved a lot.
Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest. Here we consider extending machine learning algorithms to operate on groups of data points. We suggest treating a group of data points as an i.i.d. sample set from an underlying feature dis…
Designs neural networks on matrix manifolds for improved performance in tasks like human action recognition.
problem Designing neural networks for tasks on non-Euclidean manifolds.
method Develops fully-connected and convolutional layers for SPD manifolds, and MLR on SPSD manifolds.
result Demonstrates improved performance in human action recognition and node classification tasks.
A new imputation method estimates missing values by matching observed marginals from masked data.
problem Missing values in data undermine statistical and machine learning analysis.
method Estimates a distribution from masked observations using positive semi-definite kernel density estimation.
result The method yields both single and multiple imputations from the same fitted density, with statistical consistency and fast adaptive excess risk.
Unified approach to Bayesian inference with guarantees on covariance matrices.
problem Approximate Bayesian inference with PSD guarantees.
method Bayes-Newton methods extending Newton's method for optimisation.
result Novel algorithms with PSD covariance matrices.
The paper presents two schemes for sampling matrices from specific distributions on a manifold.
problem Sampling matrices from Gibbs distributions on the manifold of positive semi-definite matrices with fixed rank.
method Two explicit schemes based on Euler-Maruyama discretization of the Riemannian Langevin equation with Brownian motion on the manifold.
result Numerical validation of the schemes using specific energy functions and metrics.
Efficient CD algorithms on matrix manifolds for optimization problems.
problem Optimization on Riemannian manifolds with computational efficiency.
method Developed coordinate descent algorithms for various matrix manifolds, updating only a few variables at each iteration.
result Proposed algorithms achieve low cost per iteration and a more efficient variant via first-order approximation.
A family of probability distributions parametrized by an open domain Λ in Rn defines the Fisher information matrix on this domain which is positive semi-definite. In information geometry the standard assumption has been that the Fisher information matrix tensor is positive definite defining in this way a Riemannia…
The study pinches rigidity theorems for minimal submanifolds in spheres.
problem Pinching rigidity theorems for minimal submanifolds in spheres.
method Analyzes the shape operators and eigenvalues of submanifolds to prove rigidity conditions.
result If certain conditions are met, the normal bundle of the submanifold is flat.
A new quasi-Newton method uses cubic regularization to avoid saddle points in deep learning.
problem Avoiding saddle points and poor local minima in deep learning models.
method Limited-memory symmetric rank-one quasi-Newton approach with adaptive regularized cubics.
result The method effectively avoids saddle points and converges to better local minima.
Establishes metrics with positive curvature on projective line bundles.
problem Existence of complete Kähler metrics with semi-positive holomorphic sectional curvature.
method Calabi's Ansatz and product approach.
result Existence of complete Kähler metrics with many zeroes.
Tseytlin has recently proposed that an action functional exists whose gradient generates to all orders in perturbation theory the Renormalization Group (RG) flow of the target space metric in the worldsheet sigma model. The gradient is defined with respect to a metric on the space of coupling constants which is explici…
Riemannian gradient descent escapes some spurious critical points on low-rank matrix manifold.
problem Spurious critical points on the boundary of low-rank matrix manifold.
method Riemannian gradient descent with dynamical low-rank approximation and rescaled gradient flow.
result Riemannian gradient descent escapes some spurious critical points on the boundary of the manifold.
Motivated by the results of B. Berndtsson, in this memoir we use the new estimates developed by W. He to extend a theorem of the second author on the existence of weak C1,1 geodesics between two smooth non-degenerate Kähler potentials to the case where the metrics on the end points may have singularities on some a…
Paper introduces a new kernel model for PSD-valued functions with theoretical guarantees and applications.
problem Enforcing positive semi-definiteness (PSD) in function models with good performance and theoretical guarantees.
method Kernel sum-of-squares model for PSD-valued functions, extending previous models for non-negative scalar functions.
result The model constitutes a universal approximator of PSD functions and can represent any smooth and strongly convex function.
Graph neural networks improve AMG convergence for sparse systems.
problem Efficiently constructing algebraic multigrid prolongation operators for sparse linear systems.
method Train a graph neural network to learn prolongation operators from matrix classes, using an unsupervised loss function.
result Improved convergence rates compared to classical AMG methods.
Energy functional on Teichmüller space is plurisubharmonic but not strictly so.
problem Characterizing points where energy functional fails to be strictly plurisubharmonic.
method Analyzing the kernel of the Levi form and relating it to Higgs bundles and Hitchin fibration.
result For generic choices, energy functional is strictly plurisubharmonic.
While the Matrix Generalized Inverse Gaussian (MGIG) distribution arises naturally in some settings as a distribution over symmetric positive semi-definite matrices, certain key properties of the distribution and effective ways of sampling from the distribution have not been carefully studied. In this paper…
This paper proposes an efficient method for sampling from stochastic differential equations using PSD models.
problem Efficient sampling from stochastic differential equations with positive semi-definite models.
method The approach leverages a PSD model to sample from the Fokker-Planck equation or its fractional variant, with a complexity of m2dlog(1/ε). result The method produces i.i.d. samples with error ε in Wasserstein-1 distance, with a cost of O(dε−2(d+1)/β−2log(1/ε)2d+3) per sample. The paper proposes methods to find a shared active subspace for multivariate vector-valued functions.
problem Minimizing the deviation between function evaluations in the original and reconstructed spaces.
method Manipulating gradients or SPD matrices to identify a shared structure.
result Summing SPD matrices often identifies the best shared active subspace.
Cuspidal edges and swallowtails are typical non-degenerate singular points on wave fronts in the Euclidean 3-space. Their first fundamental forms belong to a class of positive semi-definite metrics called "Kossowski metrics". A point where a Kossowski metric is not positive definite is called a singular point or a se…
A characterization of the proximal normal cone is obtained and a separation theorem for convex subsets of Riemannian manifolds is established. Moreover, the convexity of the distance function dS for a convex subset S in the cases where the boundary of S contains a geodesic segment, the boundary of S is C2 o…
Paper develops a new method for distribution regression with indefinite kernels.
problem Distribution regression with indefinite kernels.
method Coefficient-based regularized distribution regression with two-stage sampling.
result Optimal learning rates derived for the algorithm under mild conditions.
The paper analyzes how over-parameterization affects GD convergence in matrix sensing problems.
problem Matrix sensing problem with over-parameterized gradient descent.
method Analyzes symmetric and asymmetric parameterizations, provides lower bounds and convergence rates.
result Over-parameterization slows down GD convergence, but asymmetric parameterization can speed up convergence.
Efficiently constructs prediction bands with minimal assumptions.
problem Uncertainty quantification for nonparametric, heteroscedastic data.
method Semi-definite programming for data-adaptive prediction bands.
result Strong non-asymptotic coverage properties with minimal distributional assumptions.
Topological Data Analysis (TDA) is a recent and growing branch of statistics devoted to the study of the shape of the data. In this work we investigate the predictive power of TDA in the context of supervised learning. Since topological summaries, most noticeably the Persistence Diagram, are typically defined in comple…
The paper tackles feature cross search for linear models, providing approximation algorithms and structural results.
problem Maximizing AUC of a linear model trained on feature crosses.
method Submodular optimization, greedy algorithm, and connections to total variation and kernel matrices.
result Simple greedy (1−1/e)-approximation algorithm for maximizing AUC. Study of H-eigenvalues for complex tensors and their applications in differential geometry.
problem Characterizing H-eigenvalues of Hermitian tensors. method Introduced H-eigenvalues, derived inclusion sets, and established criteria for definiteness. result Determined inclusion sets and criteria for Hermitian and CPS tensors.
Extended elliptical slice sampling for infinite-dimensional spaces, proving reversibility.
problem Proving reversibility of elliptical slice sampling in infinite-dimensional spaces.
method Extended elliptical slice sampling to infinite-dimensional separable Hilbert spaces, providing an alternative proof of reversibility.
result The approach yields a positive semi-definite Markov operator, proving reversibility.
Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi-definite programming (\textit{SDP}), which is generally time-consuming and degrades the scalability, especially confronting large-scale dat…
Characterizes real left symmetric algebras with positive definite Koszul form and related Kähler-Einstein structures.
problem Characterizing real left symmetric algebras with positive definite Koszul form.
method Analyzes the properties of left multiplication operators and symmetric bilinear forms.
result Provides a complete characterization of real left symmetric algebras with positive definite Koszul form.