arXiv research

Decomposing tensors into orthogonal factors is a well-known task in statistics, machine learning, and signal processing. We study orthogonal outer product decompositions where the factors in the summands in the decomposition are required to be orthogonal across summands, by relating this orthogonal decomposition to the…

SOFARI improves inference on multi-task learning latent factors.

The Shapley value theory is used for risk allocation in non-orthogonal risk factors.

The paper generalizes the number of complex structures on metric Lie algebras.

A recent theoretical analysis shows the equivalence between non-negative matrix factorization (NMF) and spectral clustering based approach to subspace clustering. As NMF and many of its variants are essentially linear, we introduce a nonlinear NMF with explicit orthogonality and derive general kernel-based orthogonal m…

We classify six-dimensional Lie groups which admit a left-invariant half-flat SU(3)-structure and which split in a direct product of three-dimensional factors. Moreover, a complete list of those direct products is obtained which admit a left-invariant half-flat SU(3)-structure such that the three-dimensional factors ar…

Emergency Department (ED) crowding is a worldwide issue that affects the efficiency of hospital management and the quality of patient care. This occurs when the request for an admit ward-bed to receive a patient is delayed until an admission decision is made by a doctor. To reduce the overcrowding and waiting time of E…

Muon with Newton-Schulz converges to the same stationary point as SVD-polar, up to a constant factor.

The PARAFAC2 is a multimodal factor analysis model suitable for analyzing multi-way data when one of the modes has incomparable observation units, for example because of differences in signal sampling or batch sizes. A fully probabilistic treatment of the PARAFAC2 is desirable in order to improve robustness to noise an…

New ONMF model minimizes KL divergence for better sparse data modeling.

Spectral method for joint community detection and group synchronization.

Deep networks without non-linearities are equivalent to shallow ones.

This paper compares two stock factor models in China's A-share market.

Compact holonomy groups found in symmetric spaces.

Many modern big data applications feature large scale in both numbers of responses and predictors. Better statistical efficiency and scientific insights can be enabled by understanding the large-scale response-predictor association network structures via layers of sparse latent factors ranked by importance. Yet sparsit…

We present an algorithm for the decomposition of periodic financial return data into orthogonal factors of expected return and "systemic", "productive", and "nonproductive" risk. Generally, when the number of funds does not exceed the number of periods, the expected return of a portfolio is an affine function of its pr…

Intangible investment becomes a strong predictor of stock returns over time.

Paper proposes a new deflation varimax method for vintage factor analysis.

The non-negative matrix factorization (NMF) model with an additional orthogonality constraint on one of the factor matrices, called the orthogonal NMF (ONMF), has been found a promising clustering model and can outperform the classical K-means. However, solving the ONMF model is a challenging optimization problem becau…

We present a method based on the orthogonal symmetric non-negative matrix tri-factorization of the normalized Laplacian matrix for community detection in complex networks. While the exact factorization of a given order may not exist and is NP hard to compute, we obtain an approximate factorization by solving an optimiz…

Improves statistical learning bounds with self-concordant losses.

Muon optimizer simplifies matrix optimization with spectral orthogonalization.

New algorithms improve tensor CP decomposition under mild conditions.

In a very high-dimensional vector space, two randomly-chosen vectors are almost orthogonal with high probability. Starting from this observation, we develop a statistical factor model, the random factor model, in which factors are chosen at random based on the random projection method. Randomness of factors has the con…

We consider the problem of sampling from posterior distributions for Bayesian models where some parameters are restricted to be orthogonal matrices. Such matrices are sometimes used in neural networks models for reasons of regularization and stabilization of training procedures, and also can parameterize matrices of bo…

Study monodromy factorizations for lines on del Pezzo surfaces.

Scalable approach for high-dimensional dynamical systems with noise filtering and parameter estimation.

Tensor factorization arises in many machine learning applications, such knowledge base modeling and parameter estimation in latent variable models. However, numerical methods for tensor factorization have not reached the level of maturity of matrix factorization methods. In this paper, we propose a new method for CP te…

In this paper, we propose a scalable algorithm for spectral embedding. The latter is a standard tool for graph clustering. However, its computational bottleneck is the eigendecomposition of the graph Laplacian matrix, which prevents its application to large-scale graphs. Our contribution consists of reformulating spect…

D-GCCA improves multi-view data analysis by separating common and distinctive components.

We discuss the foundations of factor or regression models in the light of the self-consistency condition that the market portfolio (and more generally the risk factors) is (are) constituted of the assets whose returns it is (they are) supposed to explain. As already reported in several articles, self-consistency implie…

New algorithm identifies best arm in semiparametric bandits with near optimal efficiency.

Nonnegative matrix factorization (NMF) is a popular method for audio spectral unmixing. While NMF is traditionally applied to off-the-shelf time-frequency representations based on the short-time Fourier or Cosine transforms, the ability to learn transforms from raw data attracts increasing attention. However, this adds…

Study symplectic and orthogonal groups over involutive algebras, realizing geometric models for symmetric spaces and applications to Higgs bundles.

The popular Alternating Least Squares (ALS) algorithm for tensor decomposition is efficient and easy to implement, but often converges to poor local optima---particularly when the weights of the factors are non-uniform. We propose a modification of the ALS approach that is as efficient as standard ALS, but provably rec…

New method estimates latent gene expression factors without overlap with known confounders.

SVD training reduces DNN rank and computation load without SVD per step.

New method for high-dimensional manifold-based inference tackles latent responses.

New algorithm speeds up group equivariant neural networks computations.

Introduces CSLC models to bridge deep generative models and classical algorithms.

The paper diagnoses factor models using characteristic axes and zero-curve restrictions.

The paper diagnoses factor-model pricing errors using characteristic axes and bridge-alpha curves.

Gradient descent with large steps leads to chaotic parameter space and unpredictable outcomes.

New method models portfolios with leptokurtic risk factors using Gram-Charlier expansions.

We study algebraic structures ($L_\infty$ and $A_\infty$-algebras) introduced by Gaiotto, Moore and Witten in their recent work devoted to certain supersymmetric 2-dimensional massive field theories. We show that such structures can be systematically produced in any number of dimensions by using the geometry of seconda…

CP-factorization for high-dimensional tensor time series and double projection iterations

Numerous algorithms are used for nonnegative matrix factorization under the assumption that the matrix is nearly separable. In this paper, we show how to make these algorithms efficient for data matrices that have many more rows than columns, so-called "tall-and-skinny matrices". One key component to these improved met…

Neural networks learn incrementally from orthogonal data, interpolating with minimal complexity.