Efficiently factorizes coupled matrix tensor data for better accuracy and speed.
problem Poor computation efficiency in existing N-CMTF algorithms.
method Column-wise element selection to prevent frequent gradient updates.
result More accurate and computationally efficient factorization.
Paper proposes C-STM for multimodal neuroimaging data classification.
problem Multimodal neuroimaging data fusion for better classification.
method Coupled Support Tensor Machine (C-STM) using latent factors from ACMTF.
result C-STM achieves better classification performance than single-mode classifiers.
We propose a general algorithmic framework for constrained matrix and tensor factorization, which is widely used in signal processing and machine learning. The new framework is a hybrid between alternating optimization (AO) and the alternating direction method of multipliers (ADMM): each matrix factor is updated in tur…
We introduce Bayesian multi-tensor factorization, a model that is the first Bayesian formulation for joint factorization of multiple matrices and tensors. The research problem generalizes the joint matrix-tensor factorization problem to arbitrary sets of tensors of any depth, including matrices, can be interpreted as u…
Proposes a method for time-evolving and difficulty-level topic discovery.
problem Discovering evolving and advanced topics in dynamic corpora.
method Constrained Coupled Matrix-Tensor Factorization with expertise-level constraints.
result Identifies evolving and difficulty-level topics in community-contributed content.
How can we correlate neural activity in the human brain as it responds to words, with behavioral data expressed as answers to questions about these same words? In short, we want to find latent variables, that explain both the brain activity, as well as the behavioral responses. We show that this is an instance of the C…
Study quantifies performance gap between tensor and matrix-based approaches in nested matrix-tensor model.
problem Estimating a planted signal in a nested matrix-tensor model.
method Comparing tensor-based and matrix-based approaches for best rank-one approximation of tensor data.
result Derives precise algorithmic threshold for the unfolding approach and shows BBP-type transition behavior.
AMP algorithm for matrix tensor product model provides recovery conditions.
problem Generalization of standard spiked matrix models with multiple pairwise observations.
method Approximate message passing with optimal weighing and combining of estimates.
result Asymptotically exact performance description and necessary/sufficient recovery conditions.
Study on descent algorithms in spiked matrix-tensor models, revealing performance issues and solutions.
problem Analysis of descent algorithms in spiked matrix-tensor models.
method Quantitative analysis using Kac-Rice formula and PDEs for Langevin dynamics.
result Gradient flow dynamics slow down in regions with spurious local minima, while AMP performs well.
Paper finds formulas for mutual information and MMSE in matrix tensor product problems.
problem High-dimensional inference problems involving matrix tensor products.
method Single-letter formulas for mutual information and MMSE, using new techniques.
result Analytical formulas describe leading order terms in mutual information and MMSE.
Graphical notation simplifies tensor operations and decompositions.
problem Complex tensor operations are difficult to understand and represent.
method Introduces graphical notation to represent tensor operations.
result Simplified representation of tensor operations and decompositions.
Gradient-flow helps find good minima in complex models.
problem Understanding why gradient-based algorithms work in non-convex optimization.
method Kac-Rice analysis and gradient-flow from statistical physics.
result Gradient-flow finds good global minima in the presence of many spurious local minima.
Flexible framework for CMTF with ADMM for various constraints and couplings.
problem Challenges in data fusion from multiple sources with varying characteristics.
method Flexible algorithmic framework using AO and ADMM for various constraints, loss functions, and couplings.
result Accurate and computationally efficient results for various loss functions, including KL divergence.
Paper proposes an algorithm for PARAFAC2-based CMTF models with various constraints.
problem Jointly analyze matrices and tensors with irregular/ragged data.
method Alternating Optimization (AO) and ADMM for fitting PARAFAC2-based CMTF models with various constraints.
result Accurately recovers underlying patterns using various constraints and linear couplings.
Introduces nondecreasing rank for matrices and tensors, developing methods and applications.
problem Finding low-rank approximations for matrices and tensors with monotonic constraints.
method Developed a variant of hierarchical alternating least squares algorithm for finding low ND rank approximations.
result Low ND rank factorizations can be found and interpreted for real-world datasets.
Novel CGTF model for recommender systems and community detection from coupled graphs and tensors.
problem Lack of effective methods for analyzing multiple information repositories with graph side information.
method Coupled Graph-Tensor Factorization (CGTF) with ADMM for nonnegative factor recovery.
result CGTF model successfully detects communities even with missing graph links.
Bayesian Temporal Factorization predicts multidimensional time series with missing data.
problem Predicting large-scale, multidimensional spatiotemporal data with missing values.
method Integrates low-rank matrix/tensor factorization and VAR process into a probabilistic model.
result Superior performance on real-world spatiotemporal data sets compared to existing methods.
EERN uses deep learning for relational databases, outperforming other methods.
problem Deep learning for relational databases.
method Equivariant Entity-Relationship Network (EERN) using MLP equivariant to Entity-Relationship model symmetries.
result EERN outperforms other methods in synthetic and real-data experiments.
Study of Langevin algorithm in noisy high-dimensional inference.
problem Analyzing the Langevin algorithm's performance in noisy high-dimensional inference.
method Analytic study of Langevin algorithm's performances using the spiked matrix-tensor model.
result The algorithmic threshold of the Langevin algorithm is sub-optimal compared to AMP.
Study reveals efficient recovery of multi-modal signals via Bayesian methods and sequential learning.
problem Recovering multiple high-dimensional signals from correlated modalities.
method Bayesian Approximate Message Passing and Sequential Curriculum Learning.
result Sequential learning strategy optimally recovers weak signals in multi-modal settings.
Paper proposes a tensor model for clustering noisy multi-view data.
problem Clustering noisy multi-view data with non-uniform variances.
method Nested matrix-tensor model for best rank-one approximation.
result Theoretical results predict the exact accuracy of clustering.
Current high-throughput data acquisition technologies probe dynamical systems with different imaging modalities, generating massive data sets at different spatial and temporal resolutions posing challenging problems in multimodal data fusion. A case in point is the attempt to parse out the brain structures and networks…
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…
This paper sets fundamental limits for rank-one matrix estimation with varying noise levels.
problem Estimating a rank-one matrix from Gaussian observations with different noise levels across blocks.
method Novel reduction from heterogeneous noise to homogeneous noise, proving asymptotic error bounds.
result Asymptotically exact formulas for minimum mean-squared error in estimating rank-one matrix and factors.
We study low rank matrix and tensor completion and propose novel algorithms that employ adaptive sampling schemes to obtain strong performance guarantees. Our algorithms exploit adaptivity to identify entries that are highly informative for learning the column space of the matrix (tensor) and consequently, our results …
Study accelerates optimization methods in non-convex problems, but doesn't improve the algorithm's performance.
problem Understanding the behavior of momentum-based acceleration methods in non-convex, high-dimensional landscapes.
method Used dynamical mean field theory to describe the average dynamics of heavy-ball momentum and Nesterov acceleration in a non-convex model.
result Accelerated dynamics but did not improve the algorithm's performance with respect to gradient descent.
We provide an end-to-end differentially private spectral algorithm for learning LDA, based on matrix/tensor decompositions, and establish theoretical guarantees on utility/consistency of the estimated model parameters. The spectral algorithm consists of multiple algorithmic steps, named as "{edges}", to which noise cou…
IGNNK uses GNN for spatiotemporal kriging, improving scalability and transferability.
problem Efficiently recovering signals for unsampled locations in spatiotemporal data.
method Developed an Inductive Graph Neural Network Kriging (IGNNK) model to learn spatial message passing.
result IGNNK effectively learns spatial message passing and can be transferred to new graph structures.
Paper extends SMM to weakly convex and multi-convex surrogates for non-convex optimization.
problem Non-convex optimization with weakly convex or multi-convex surrogates.
method Stochastic majorization-minimization with proximal regularization or block-minimization.
result Convergence rates for empirical and expected losses under non-i.i.d. data.
A new method for filling in missing traffic data improves accuracy over existing techniques.
problem Incomplete spatiotemporal traffic data.
method Low-rank autoregressive tensor completion (LATC) framework.
result LATC framework better captures spatiotemporal consistency and local consistency.
A new algorithm improves both computational efficiency and statistical optimality for robust low-rank matrix and tensor estimation.
problem Challenges in low-rank matrix estimation under heavy-tailed noise, both computationally and statistically.
method Riemannian sub-gradient (RsGrad) algorithm, which is computationally efficient and statistically optimal.
result RsGrad achieves linear convergence and statistical optimality for robust loss functions under Gaussian and heavy-tailed noise.
Develops a deep multi-factor model for factor investing with clear financial insights.
problem Lack of interpretability and unclear financial insights in non-linear factor models.
method Industry and market neutralization modules, graph attention modules, factor-attention module.
result Demonstrates effectiveness in factor investing with real-world stock market data.
Factor Engine simplifies financial factor computation and analysis in Python.
problem Efficient computation and analysis of financial factors.
method Modular, extensible Python library with decorators, integrates with data science ecosystem.
result Mispricing factors computed by Factor Engine and Stata implementation are highly similar.
New risk factors improve stress testing accuracy.
problem Improving stress testing accuracy with new risk factors.
method Adapted PCA and autoencoders for dimension reduction and interpretation.
result Aggregated risk factors enhance stress testing outcomes.
New statistical factors improve portfolio risk estimation.
problem Improving estimation of portfolio risk using new statistical factors.
method Matrix factor models and statistical methods (partial F test, double selection LASSO).
result New statistical factors add explanatory power in asset pricing.
Introduces factor risk measures to assess risk relative to multiple factors.
problem Measuring risk relative to multiple factors.
method Introduces a double-argument mapping as a risk measure to assess risk relative to a vector of factors.
result Characterizes various types of factor risk measures including distortion, quantile, linear, and coherent measures.
AlphaLogics mines market logic to generate interpretable alpha factors.
problem Complex, opaque alpha factors from factor mining overlook market logic.
method Market Logic Mining, Factor Generation and Optimization, Market Logic Generation and Optimization.
result AlphaLogics improves predictive metrics and risk-adjusted returns over baselines.
Method learns shared and specific factors in multi-study gene expression data.
problem Understanding shared and specific factors in high-dimensional multi-study data.
method Nonlinear multi-study factor model with sparse variational autoencoder.
result Method recovers meaningful shared and specific factors in platelet gene expression data.
FactorGCL uses hypergraph learning to predict stock returns by mining hidden factors.
problem Mining effective factors in data-driven models is challenging due to low signal-to-noise ratio in market data.
method FactorGCL employs a hypergraph structure and temporal residual contrastive learning to extract hidden factors.
result FactorGCL outperforms existing methods and mines effective hidden factors for predicting stock returns.
We propose a nonparametric Bayesian factor regression model that accounts for uncertainty in the number of factors, and the relationship between factors. To accomplish this, we propose a sparse variant of the Indian Buffet Process and couple this with a hierarchical model over factors, based on Kingman's coalescent. We…
We present a novel factor analysis method that can be applied to the discovery of common factors shared among trajectories in multivariate time series data. These factors satisfy a precedence-ordering property: certain factors are recruited only after some other factors are activated. Precedence-ordering arise in appli…
The paper derives a formula for factorizing categorical data to improve Bayes classifiers.
problem Improving the accuracy of Bayes classifiers by effectively factoring multidimensional data.
method Derives an explicit formula for calculating the marginal likelihood of a factorized categorical dataset.
result The derived formula can be used to select the best factorization for constructing a Bayes classifier.
We propose a framework for constructing factor models for alpha streams. Our motivation is threefold. 1) When the number of alphas is large, the sample covariance matrix is singular. 2) Its out-of-sample stability is challenging. 3) Optimization of investment allocation into alpha streams can be tractable for a factor …
A study finds that only a few factors explain corporate bond risk, rendering extensive bond factor literature redundant.
problem The redundancy of extensive bond factor literature in explaining corporate bond risk premia.
method Bayesian Model Averaging Stochastic Discount Factor analysis of 18 quadrillion models.
result A Bayesian Model Averaging SDF explains risk premia better than low-dimensional models, with an out-of-sample Sharpe ratio of 1.5 to 1.8.
Large language models improve futures market factor models in China.
problem Designing effective factor models for Chinese futures markets.
method Used large language models (GPT) to generate 40 factors for single and multi-factor portfolios.
result GPT-generated factors outperform benchmarks with high Sharpe ratios and alphas.
New tests for identifying the number of latent factors in short panels with small time dimensions.
problem Determining the number of latent factors in short panels with small time dimensions.
method Eigenvalue tests based on variance-covariance matrices of asset returns, with assumptions on spherical errors or instrumental variables for factor betas.
result Established asymptotic distributional results and proposed a novel statistical test for weak factors.
Optimal tensor PCA for estimating factors and loadings in high-dimensional panel data.
problem Estimating factors and loadings in high-dimensional panel data with non-negligible correlations.
method Tensor Principal Component Analysis (TPCA) for estimating factors and loadings in a tensor factor model.
result Simple TPCA is optimal for strong factors and can be improved for weak factors with alternating least-squares iterations.
Paper proposes NNAFC for automatic financial factor construction.
problem Manual factor construction is time-consuming and prone to bias.
method NNAFC uses neural networks to automatically construct diversified financial factors.
result NNAFC outperforms GP in constructing more informative and diversified factors.