arXiv research

LEGO estimates tangent spaces more robustly than LPCA in noisy data.

The paper tackles learning symmetries in data without expert knowledge.

The problem of estimating sparse eigenvectors of a symmetric matrix attracts a lot of attention in many applications, especially those with high dimensional data set. While classical eigenvectors can be obtained as the solution of a maximization problem, existing approaches formulate this problem by adding a penalty te…

We provide new examples of diffusion operators in dimension 2 and 3 which have orthogonal polynomials as eigenvectors. Their construction rely on the finite subgroups of O(3) and their invariant polynomials.

Unified framework for multi-view learning with orthogonal projections.

SpecNet2 improves spectral embedding without orthogonalization, achieving better performance and efficiency.

The study extends Jacobi-orthogonality to indefinite scalar product spaces.

EigenGame reinterprets PCA as a game to find eigenvectors.

Spectral methods achieve near-optimal performance in orthogonal and permutation group synchronization.

Sign equivariant networks improve model expressiveness for spectral geometric learning.

We propose a general framework to study the stability of the subspace spanned by $P$ consecutive eigenvectors of a generic symmetric matrix ${\bf H}_0$, when a small perturbation is added. This problem is relevant in various contexts, including quantum dissipation (${\bf H}_0$ is then the Hamiltonian) and risk control …

New mathematical foundations for stable RKHSs improve system identification.

In this paper, we apply tools from the random matrix theory (RMT) to estimates of correlations across volatility of various assets in the S&P 500. The volatility inputs are estimated by modeling price fluctuations as GARCH(1,1) process. The corresponding correlation matrix is constructed. It is found that the distribut…

In many applications, one has side information, e.g., labels that are provided in a semi-supervised manner, about a specific target region of a large data set, and one wants to perform machine learning and data analysis tasks "nearby" that prespecified target region. For example, one might be interested in the clusteri…

Random matrix ensembles yield uniform distributions on manifolds.

We use methods of random matrix theory to analyze the cross-correlation matrix C of price changes of the largest 1000 US stocks for the 2-year period 1994-95. We find that the statistics of most of the eigenvalues in the spectrum of C agree with the predictions of random matrix theory, but there are deviations for a fe…

Algorithm estimates principal eigenvector with adaptive sensing, improving over non-adaptive methods.

We propose a general framework to study the stability of the subspace spanned by $P$ consecutive eigenvectors of a generic symmetric matrix ${\bf H}_0$, when a small perturbation is added. This problem is relevant in various contexts, including quantum dissipation (${\bf H}_0$ is then the Hamiltonian) and financial ris…

We analyze cross-correlations between price fluctuations of different stocks using methods of random matrix theory (RMT). Using two large databases, we calculate cross-correlation matrices C of returns constructed from (i) 30-min returns of 1000 US stocks for the 2-yr period 1994--95 (ii) 30-min returns of 881 US stock…

Study rigid classes on hyperkahler manifolds, showing general ones are rigid.

New formulas for flag manifolds simplify eigenvector perturbation.

We introduce a novel harmonic analysis for functions defined on the vertices of a strongly connected directed graph of which the random walk operator is the cornerstone. As a first step, we consider the set of eigenvectors of the random walk operator as a non-orthogonal Fourier-type basis for functions over directed gr…

A new classifier uses weighted orthogonal regression for robust classification with limited data.

I introduce Forecastable Component Analysis (ForeCA), a novel dimension reduction technique for temporally dependent signals. Based on a new forecastability measure, ForeCA finds an optimal transformation to separate a multivariate time series into a forecastable and an orthogonal white noise space. I present a converg…

New method trains neural networks in spectral domain for improved performance.

Introduces tunable basis functions for Gaussian processes.

A new method for sparse PCA using orthogonal rotations and soft-thresholding.

Study eigenvector overlaps in large Gaussian matrices, simplifying for GOE.

Latent variable models with hidden binary units appear in various applications. Learning such models, in particular in the presence of noise, is a challenging computational problem. In this paper we propose a novel spectral approach to this problem, based on the eigenvectors of both the second order moment matrix and t…

New method identifies structural parameters without assuming uncorrelated errors.

Machine learning models perform better with location coordinates alone, not Moran Eigenvectors.

Autoencoder performance is predicted by eigenvalues of weight matrices.

Paper addresses eigenvector perturbation in small eigen-gap scenarios.

We calculate eigenvector overlaps between intersecting time periods of covariance matrices.

A new methodology has been introduced to clean the correlation matrix of single stocks returns based on a constrained principal component analysis using financial data. Portfolios were introduced, namely "Fundamental Maximum Variance Portfolios", to capture in an optimal way the risks defined by financial criteria ("Bo…

This work improves disentanglement in latent space models without sacrificing generation quality.

In spectral clustering, one defines a similarity matrix for a collection of data points, transforms the matrix to get the Laplacian matrix, finds the eigenvectors of the Laplacian matrix, and obtains a partition of the data using the leading eigenvectors. The last step is sometimes referred to as rounding, where one ne…

We study distributed computing of the truncated singular value decomposition problem. We develop an algorithm that we call \texttt{LocalPower} for improving communication efficiency. Specifically, we uniformly partition the dataset among $m$ nodes and alternate between multiple (precisely $p$) local power iterations an…

We study the problem asking if one can embed manifolds into finite dimensional Euclidean spaces by taking finite number of eigenvector fields of the connection Laplacian. This problem is essential for the dimension reduction problem in massive data analysis. Singer-Wu proposed the vector diffusion map which embeds mani…

New metric tensor field on symmetric matrices simplifies eigenvector computation.

This paper introduces a novel framework for generative models based on Restricted Kernel Machines (RKMs) with joint multi-view generation and uncorrelated feature learning, called Gen-RKM. To enable joint multi-view generation, this mechanism uses a shared representation of data from various views. Furthermore, the mod…

Study the spectrum of Poincaré operator in triaxial ellipsoids.

Spectral clustering performance depends on eigenvector fluctuations, shown to be Gaussian.

New neural architectures invariant to sign flips and basis symmetries for graph representation learning.

New algorithm updates eigenvectors of evolving graphs efficiently.

How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix? For a wide family of distributions, including distributions with finite second moment and distributions supported in a centered Euclidean ball, we prove …

A special Kähler-Ricci potential on a Kähler manifold is any nonconstant $C^\infty$ function $τ$ such that $J(\nablaτ)$ is a Killing vector field and, at every point with $dτ\ne 0$, all nonzero tangent vectors orthogonal to $\nablaτ$ and $J(\nablaτ)$ are eigenvectors of both $\nabla dτ$ and the Ricci tensor. For instan…

New theory for eigenvectors of generalized Laplacian matrices, addressing dependency issues.