arXiv research

Analyzes canonical reductive decomposition of extrinsic homogeneous submanifolds.

IKD uses eigen-decomposition for nonlinear dimensionality reduction.

Two methods preserve tensor structure for reduced dimensionality in tensor regression.

Proposes a faster Isomap algorithm by reducing eigenvalue decomposition complexity.

This work improves tensor decomposition methods, especially for large datasets.

Study classifies metrics on anti-de Sitter spacetime with specific symmetries.

We present a method for fast resting-state fMRI spatial decomposi-tions of very large datasets, based on the reduction of the temporal dimension before applying dictionary learning on concatenated individual records from groups of subjects. Introducing a measure of correspondence between spatial decompositions of rest …

In this paper an extended CPR decomposition theorem for Finsler symmetric spaces of semi-negative curvature in the context of reductive structures is proven. This decomposition theorem is applied to give a geometric description of the complexification of some infinite dimensional homogeneous spaces.

Geodesic orbit and weakly symmetric properties in spray geometry.

Paper compresses RNNs using HT decomposition for better performance.

In this article, we achieved several non-naturally reductive Einstein metrics on exceptional simple Lie groups, which are formed by the decomposition arising from general Wallach spaces. By using the decomposition corresponding to the two involutive automorphisms, we calculated the non-zero coefficients in the expressi…

Reductive G-structures on a principal bundle Q are considered. It is shown that these structures, i.e. reductive G-subbundles P of Q, admit a canonical decomposition of the pull-back vector bundle $i_P^*(TQ) = P \times_Q TQ$ over P. For classical G-structures, i.e. reductive G-subbundles of the linear frame bundle, suc…

New findings on Codazzi tensors in homogeneous spaces.

IRCUR accelerates RPCA by using CUR decomposition for efficient low rank estimation.

We develop a holonomy reduction procedure for general Cartan geometries. We show that, given a reduction of holonomy, the underlying manifold naturally decomposes into a disjoint union of initial submanifolds. Each such submanifold corresponds to an orbit of the holonomy group on the modelling homogeneous space and car…

Matrix factorizations and their extensions to tensor factorizations and decompositions have become prominent techniques for linear and multilinear blind source separation (BSS), especially multiway Independent Component Analysis (ICA), NonnegativeMatrix and Tensor Factorization (NMF/NTF), Smooth Component Analysis (Smo…

SVD-based methods reduce computational cost for stochastic systems.

Supervised dimensionality reduction strategies have been of great interest. However, current supervised dimensionality reduction approaches are difficult to scale for situations characterized by large datasets given the high computational complexities associated with such methods. While stochastic approximation strateg…

In statistical learning, high covariate dimensionality poses challenges for robust prediction and inference. To address this challenge, supervised dimension reduction is often performed, where dependence on the outcome is maximized for a selected covariate subspace with smaller dimensionality. Prevalent dimension reduc…

Paper applies ANOVA decomposition for interpretable data approximation.

This paper studies how key tensor properties are inherited in subtensors of tensor train decompositions.

Geodesic orbit spaces and their families are studied in pseudo-Riemannian manifolds.

A novel hypergraph partitioning method using tensor eigenvalue decomposition captures super-dyadic interactions.

Scalable and robust TR decomposition for large-scale data with missing entries and outliers.

New method models matrix time series using tensor CP-decomposition.

In this paper we consider the use of the space vs. time Kronecker product decomposition in the estimation of covariance matrices for spatio-temporal data. This decomposition imposes lower dimensional structure on the estimated covariance matrix, thus reducing the number of samples required for estimation. To allow a sm…

Paper proposes efficient BNN inference flow to reduce computation and memory costs.

Criterion for polystability in Lie group actions on manifolds.

We present local discriminative Gaussian (LDG) dimensionality reduction, a supervised dimensionality reduction technique for classification. The LDG objective function is an approximation to the leave-one-out training error of a local quadratic discriminant analysis classifier, and thus acts locally to each training po…

Starting from the general concept of a Lie derivative of an arbitrary differentiable map, we develop a systematic theory of Lie differentiation in the framework of reductive G-structures P on a principal bundle Q. It is shown that these structures admit a canonical decomposition of the pull-back vector bundle i_P^*(TQ)…

Classifies compact Clifford-Klein forms for specific Lie algebras.

Paper explores how risk-averse individuals' willingness to pay for insurance varies with risk probability.

A fair PCA method using JEVD ensures balanced data representation.

Nielsen reduction is an algorithm which decomposes any automorphism of a free group into a product of elementary Nielsen transformations. While this may be applied to a mapping class of a surface $S_{g,1}$ with one boundary component, the resulting decomposition in general will not have a topological interpretation. In…

This thesis explores fast algorithms for large matrices and data augmentation to improve model efficiency.

Large textual corpora are often represented by the document-term frequency matrix whose elements are the frequency of terms; however, this matrix has two problems: sparsity and high dimensionality. Four dimension reduction strategies are used to address these problems. Of the four strategies, unsupervised feature trans…

Neural Decomposition breaks down VAE latent structure for better interpretability.

Review and compare model order reduction methods for process engineering.

CW-EDMD improves prediction accuracy by learning local Koopman models for different state-space regions.

Variables in many massive high-dimensional data sets are structured, arising for example from measurements on a regular grid as in imaging and time series or from spatial-temporal measurements as in climate studies. Classical multivariate techniques ignore these structural relationships often resulting in poor performa…

Invariant polynomials improve machine learning performance.

We study finite dimensional almost and quasi-effective prolongations of nilpotent Z-graded Lie algebras, especially focusing on those having a decomposable reductive structural subalgebra. Our assumptions generalize effectiveness and algebraicity and are appropriate to obtain Levi-Malčev and Levi-Chevalley decompositio…

Study on special Lie groups with Lorentzian metrics.

New method uses tensor decomposition to improve noise reduction in machine fault detection.

In this article, we consider the sparse tensor singular value decomposition, which aims for dimension reduction on high-dimensional high-order data with certain sparsity structure. A method named Sparse Tensor Alternating Thresholding for Singular Value Decomposition (STAT-SVD) is proposed. The proposed procedure featu…

This paper investigates the hedging effectiveness of a dynamic moving window OLS hedging model, formed using wavelet decomposed time-series. The wavelet transform is applied to calculate the appropriate dynamic minimum-variance hedge ratio for various hedging horizons for a number of assets. The effectiveness of the dy…

Study geodesic orbit Lorentz nilmanifolds, proving structural properties.

Reductive (or semisimple) algebraic groups, Lie groups and Lie algebras have a rich geometry determined by their parabolic subgroups and subalgebras, which carry the structure of a building in the sense of J. Tits. We present herein an elementary approach to the geometry of parabolic subalgebras, over an arbitrary fiel…