Adaptive estimation in structured factor models with applications to overlapping clustering
From MaRDI portal
Publication:2215724
Abstract: This work introduces a novel estimation method, called LOVE, of the entries and structure of a loading matrix A in a sparse latent factor model X = AZ + E, for an observable random vector X in Rp, with correlated unobservable factors Z in RK, with K unknown, and independent noise E. Each row of A is scaled and sparse. In order to identify the loading matrix A, we require the existence of pure variables, which are components of X that are associated, via A, with one and only one latent factor. Despite the fact that the number of factors K, the number of the pure variables, and their location are all unknown, we only require a mild condition on the covariance matrix of Z, and a minimum of only two pure variables per latent factor to show that A is uniquely defined, up to signed permutations. Our proofs for model identifiability are constructive, and lead to our novel estimation method of the number of factors and of the set of pure variables, from a sample of size n of observations on X. This is the first step of our LOVE algorithm, which is optimization-free, and has low computational complexity of order p2. The second step of LOVE is an easily implementable linear program that estimates A. We prove that the resulting estimator is minimax rate optimal up to logarithmic factors in p. The model structure is motivated by the problem of overlapping variable clustering, ubiquitous in data science. We define the population level clusters as groups of those components of X that are associated, via the sparse matrix A, with the same unobservable latent factor, and multi-factor association is allowed. Clusters are respectively anchored by the pure variables, and form overlapping sub-groups of the p-dimensional random vector X. The Latent model approach to OVErlapping clustering is reflected in the name of our algorithm, LOVE.
Recommendations
- Lowdimensional additive overlapping clustering
- Model selection in overlapping stochastic block models
- Sparsest factor analysis for clustering variables: a matrix decomposition approach
- Model assisted variable clustering: minimax-optimal recovery and algorithms
- Clustering multivariate data using factor analytic Bayesian mixtures with an unknown number of components
Cites work
- A constrained \(\ell _{1}\) minimization approach to sparse precision matrix estimation
- A fast algorithm with minimax optimal guarantees for topic models with an unknown number of topics
- Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas
- Adaptive estimation of the rank of the coefficient matrix in high-dimensional multivariate response regression models
- Determining the Number of Factors in Approximate Factor Models
- EM algorithms for ML factor analysis
- Estimating sparse precision matrix: optimal rates of convergence and adaptive estimation
- Generic global identification in factor analysis
- High-dimensional graphs and variable selection with the Lasso
- High-dimensional sparse factor modeling: applications in gene expression genomics
- scientific article; zbMATH DE number 3117083 (Why is no real title available?)
- scientific article; zbMATH DE number 3934234 (Why is no real title available?)
- scientific article; zbMATH DE number 3793445 (Why is no real title available?)
- scientific article; zbMATH DE number 45532 (Why is no real title available?)
- scientific article; zbMATH DE number 1964693 (Why is no real title available?)
- scientific article; zbMATH DE number 3396952 (Why is no real title available?)
- Identifiability of factor analysis: Some results and open problems
- Large covariance estimation by thresholding principal orthogonal complements. With discussion and authors' reply
- Latent variable graphical model selection via convex optimization
- Linear and conic programming estimators in high dimensional errors-in-variables models
- Model assisted variable clustering: minimax-optimal recovery and algorithms
- Model selection and estimation in the Gaussian graphical model
- Modern Multivariate Statistical Techniques
- Optimal selection of reduced rank estimators of high-dimensional matrices
- Rank-reducibility of a symmetric matrix and sampling theory of minimum trace factor analysis
- Rank-Sparsity Incoherence for Matrix Decomposition
- Robust Matrix Decomposition With Sparse Corruptions
- Robust principal component analysis?
- Sparse Bayesian infinite factor models
- Sparse inverse covariance estimation with the graphical lasso
- Statistical analysis of factor models of high dimension
- The asymptotic normal distribution of estimators in factor analysis under general conditions
- The Identification of Structural Characteristics
Cited in
(17)- Statistical inference for structured high-dimensional models. Abstracts from the workshop held March 11--17, 2018
- Inference in latent factor regression with clusterable features
- Model assisted variable clustering: minimax-optimal recovery and algorithms
- A note on identifiability conditions in confirmatory factor analysis
- Detecting approximate replicate components of a high-dimensional random vector with latent structure
- scientific article; zbMATH DE number 7255095 (Why is no real title available?)
- Nonsparse learning with latent variables
- Structured latent factor analysis for large-scale data: identifiability, estimability, and their implications
- Spectral deconfounding via perturbed sparse linear models
- scientific article; zbMATH DE number 7415120 (Why is no real title available?)
- A Joint MLE Approach to Large-Scale Structured Latent Attribute Analysis
- A Doubly Enhanced EM Algorithm for Model-Based Tensor Clustering
- Optimal discriminant analysis in high-dimensional latent factor models
- Optimal vintage factor analysis with deflation varimax
- Algebraic sparse factor analysis
- Blessing of dependence: identifiability and geometry of discrete models with multiple binary latent variables
- Toward Interpretable Deep Generative Models via Causal Representation Learning
This page was built for publication: Adaptive estimation in structured factor models with applications to overlapping clustering
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2215724)
