Proposes D-CDLF for multi-view data decomposition.
problem Uncorrelatedness between common and distinctive latent factors.
method Decomposes data into common, distinctive, and noise components.
result Effective uncorrelatedness between distinctive latent factors from different views.
Bayesian neural networks decompose uncertainty into epistemic and aleatoric components.
problem Uncertainty in Bayesian neural networks with latent variables.
method Information theoretic approach and risk-sensitive objective for safe reinforcement learning.
result Natural decomposition of predictive uncertainty in Bayesian active learning and safe RL.
This work considers a computationally and statistically efficient parameter estimation method for a wide class of latent variable models---including Gaussian mixture models, hidden Markov models, and latent Dirichlet allocation---which exploits a certain tensor structure in their low-order observable moments (typically…
The paper refines disentanglement in VAEs by defining it as latent overlap and prior structure.
problem Improving the disentanglement of latent variables in Variational Autoencoders (VAEs).
method Develops a new perspective on disentanglement as latent overlap and prior structure, and introduces a training objective to control both factors.
result The β-VAE controls latent overlap and maintains prior structure, leading to better disentanglement. Paper detects and mitigates concept drift in streaming tensor decompositions.
problem Variability of latent concepts over time in dynamic data streams.
method SeekAndDestroy algorithm for detecting and mitigating concept drift.
result SeekAndDestroy effectively detects and mitigates concept drift in streaming tensor decompositions.
Neural Decomposition breaks down VAE latent structure for better interpretability.
problem Limited interpretability of VAE latent representations.
method Adapted functional ANOVA to VAEs, applying constraints for identifiability.
result Decomposes data variation into latent and fixed input effects.
New method handles missing data for tensor decomposition.
problem Learning latent variables from partial data.
method Weighted tensor decomposition approach for incomplete data.
result Weighted approach outperforms non-weighted methods.
VDA improves disentanglement of latent representations in complex signals.
problem Learning disentangled and interpretable representations in nonstationary, high-dimensional time-evolving signals.
method Variational decomposition autoencoding (VDA) framework, incorporating signal decomposition, contrastive self-supervised task, and variational prior approximation.
result DecVAEs surpass state-of-the-art VAE-based methods in disentanglement quality and generalization.
New algorithm for latent variable models using spectral decomposition.
problem Unsupervised learning of latent variable models from unlabeled data.
method Spectral decomposition for robust unsupervised learning.
result Efficient technique to learn parameters of text mining models.
LSD framework decomposes variable-length sequences.
problem Sequence recognition with variable-length outputs.
method Training algorithm samples valid extensions; approximate decoding algorithm.
result LSD model reduces WER to 12.9% on Wall Street Journal task.
Efficient tensor completion method using rank minimization on TR latent space.
problem High model sensitivity and exponential model possibilities in TR decomposition.
method Nuclear norm regularization on latent TR factors, ADMM scheme.
result Superior performance and efficiency compared to state-of-the-art algorithms.
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…
ALℓ0CORE tensor decomposition reduces computational cost for sparse count data.
problem Efficiently decompose sparse count data matrices.
method Probabilistic Tucker decomposition with ℓ0-norm constraint. result ALℓ0CORE achieves similar results to full Tucker decomposition at a fraction of the cost. Proposes a Gaussian process for Koopman mode decomposition.
problem Estimating Koopman mode decomposition quantities and latent variables.
method Unsupervised Gaussian process for simultaneous estimation.
result Efficient parameter estimation through low-rank approximations.
Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas. Compared to standard Latent Semantic Analysis which s…
DiCoLa recursively decomposes causal structure learning for latent variables.
problem Learning causal structures in high-dimensional settings with latent variables.
method Recursive decomposition framework for divide-and-conquer causal discovery.
result Theoretical soundness and completeness of DiCoLa framework.
Spectral learning extends matrix methods to tensors for better latent variable modeling.
problem Limitations of matrix-based spectral methods in capturing non-Gaussian data.
method Extend spectral decomposition to tensor-based methods for higher-order moments.
result Tensor decomposition can identify latent effects missed by matrix methods.
Framework fine-tunes foundation models with semi-supervised learning for downstream tasks and latent spaces.
problem Training foundation models with limited labelled data.
method Mutual information decomposition for downstream and latent spaces, semi-supervised fine-tuning.
result Significant improvements in classification tasks under low-labelled conditions.
Paper identifies latent factors from noisy measurements using tensor decomposition.
problem Identification of latent factors from noisy, correlated measurements.
method Tensor decomposition of third order cross moments, Kruskal theorem, Kotlarski identity, generalized Kruskal rank.
result Full distribution of latent factors and measurement errors identified without injective measurements.
A new tensor model merges curve registration and tensor decomposition.
problem Retrieving latent factors and diffeomorphisms from data slices.
method Introduced a registered CP tensor model with a diffeomorphism constraint.
result Simulation results show registered CP outperforms other models.
We discuss structured Schatten norms for tensor decomposition that includes two recently proposed norms ("overlapped" and "latent") for convex-optimization-based tensor decomposition, and connect tensor decomposition with wider literature on structured sparsity. Based on the properties of the structured Schatten norms,…
IKD uses eigen-decomposition for nonlinear dimensionality reduction.
problem Lack of sophisticated and nonlinear dimensionality reduction methods.
method Inverse Kernel Decomposition (IKD) based on eigen-decomposition of sample covariance matrix.
result IKD achieves comparable performance to optimization-based methods with faster running speeds.
DiPCA algorithm improves scalability and solution quality for time-dependent data.
problem Analyzing time-dependent multivariate data with dynamic latent variables.
method Solves a large-scale, dense, nonconvex NLP using a scalable decomposition algorithm.
result The decomposition algorithm is a specialized coordinate maximization algorithm, explaining its performance and guiding improvements.
Paper shows how SFA fits into FBM framework for time series separation.
problem Identifying time series decomposition in flow-based models.
method Combining SFA and FBM to make time series decomposition identifiable.
result Time series decomposition becomes identifiable using SFA and FBM.
Paper learns noisy-or networks efficiently using tensor decomposition.
problem Efficiently learning noisy-or networks with tensor decomposition.
method Tensor decomposition for noisy-or networks, considering systematic error.
result Provable efficient learning algorithm for noisy-or networks.
New method identifies latent variables with causal dependencies from observed data.
problem Identify latent variables with causal relationships from observed data.
method Linear causal disentanglement via higher-order cumulants, with perfect and soft interventions.
result Recovery of parameters via coupled tensor decomposition and polynomial equations.
Improved spectral methods of moments for robust latent variable model learning.
problem Limited robustness of spectral methods of moments to model misspecification.
method Hierarchical approach using approximate joint diagonalization instead of tensor decomposition.
result Our method outperforms previous tensor decomposition methods in speed and model quality.
HCL learns shared and modality-specific latent representations for multimodal data.
problem Binary shared-private decomposition inadequately represents shared information across subsets of modalities.
method Hierarchical Contrastive Learning framework combining latent-variable formulation, structural sparsity, and contrastive objective.
result HCL accurately recovers hierarchical structure and improves predictive performance on multimodal data.
Method determines latent dimensionality in international trade flows.
problem Finding meaningful low-dimensional latent features in high-dimensional international trade data.
method Proposes a latent dimension determination method based on clustering of nonnegative RESCAL decompositions.
result Validates the latent features against empirical economic facts.
ED-VAE improves VAEs by explicitly including entropy components in ELBO.
problem Limitations of traditional VAEs with ELBO in generating high-quality samples and interpreting latent spaces.
method Introduces ED-VAE, a re-formulation of ELBO that includes entropy and cross-entropy components.
result Significantly enhances model flexibility and improves interpretability and generative performance.
New framework assesses value of labeled vs unlabeled data in latent variable models.
problem Determining the optimal use of labeled and unlabeled data in latent variable models.
method Developed a bias-variance decomposition of the generalization error for method-of-moments latent variable estimation, and introduced a correction for misspecification.
result Labeled data is more valuable than unlabeled data when models are misspecified, but this value can be reduced with correction.
Paper introduces TSSDMN for modeling dynamic multilayer networks.
problem Capturing temporal and cross-layer dynamics in multilayer networks.
method Tensor State Space Model (TSSDMN) using symmetric Tucker decomposition.
result TSSDMN uniquely captures temporal dynamics within and across layers.
FunBaT extends Tucker decomposition to handle continuous-indexed tensor data.
problem Handling continuous-indexed tensor data that doesn't fit traditional Tucker decomposition.
method FunBaT treats continuous-indexed data as interactions between a core tensor and a group of latent functions modeled by Gaussian processes (GP). It converts each GP into a state-space prior and uses advanced message-passing techniques for scalable inference.
result FunBaT effectively handles real-world data with continuous indexes, demonstrating its advantage in synthetic and real-world applications.
Paper proposes a novel spectral approach to learn binary latent variable models.
problem Learning binary latent variable models with hidden binary units in noisy data.
method Spectral approach based on eigenvectors of second and third order moment matrices.
result Consistently estimates model parameters at optimal rate under mild conditions.
New method proves exact recovery for tensor decomposition under reshuffling.
problem Numerical defects limit practical applications of tensor decomposition.
method Proves exact-recovery property for latent convex tensor decomposition using reshuffling.
result Generalized LCTD achieves exact recovery under reshuffling.
Overcomplete latent representations have been very popular for unsupervised feature learning in recent years. In this paper, we specify which overcomplete models can be identified given observable moments of a certain order. We consider probabilistic admixture or topic models in the overcomplete regime, where the numbe…
Bayesian neural networks decompose uncertainty into epistemic and aleatoric components for efficient and risk-sensitive learning.
problem Uncertainty in Bayesian neural networks estimation of weights and complex noise patterns in data.
method Decomposition of uncertainty into epistemic and aleatoric components, and definition of a risk-sensitive criterion for reinforcement learning.
result Identification of informative points for active learning and policies balancing expected cost, model-bias, and noise aversion.
This work improves fair tensor decomposition using a kernel criterion.
problem Learning fair low-rank tensor decompositions with statistical parity.
method Regularizes Canonical Polyadic Decomposition with KHSIC to ensure approximate statistical parity.
result The proposed algorithm achieves better fairness and fit than state-of-the-art FATR.
D-GCCA improves multi-view data analysis by separating common and distinctive components.
problem Analyzing multi-view high-dimensional data with latent factors.
method Decomposes each view's data matrix into common and distinctive sources with orthogonality constraints.
result Consistent estimators with good performance and efficient computation.
New method for MAP inference using Benders' decomposition.
problem Finite-time convergence guarantee for MAP inference.
method Sequentially adding constraints using Benders' decomposition.
result Higher optimal posterior value compared to other methods.
We introduce Bayesian Poisson Tucker decomposition (BPTD) for modeling country--country interaction event data. These data consist of interaction events of the form "country i took action a toward country j at time t." BPTD discovers overlapping country--community memberships, including the number of latent com…
A novel algorithm converges for solving a specific matrix decomposition problem.
problem Nonlinear matrix decomposition with ReLU function for sparse data.
method Introduced a reparametrization of the Latent-RMD model and developed eBCD for convergence proof.
result eBCD converges and outperforms state-of-the-art methods on various data sets.
Proposes a method to learn sparse and low-rank interactions in Ising models with latent variables.
problem Learning sparse interactions in Ising models with latent variables.
method Sparse + low-rank decomposition of Ising model parameters using convex regularized likelihood problem.
result Consistency properties in high-dimensional settings with growing number of variables and samples.
A method decomposes battery cell capacity trends using MCGP for high accuracy and uncertainty.
problem Forecasting lithium-ion battery cells capacity with high accuracy and uncertainty.
method Multi-Output Convolved Gaussian Process (MCGP) for latent function decomposition.
result The MCGP method provides high prediction accuracy and uncertainty information.
We present an approach for penalized tensor decomposition (PTD) that estimates smoothly varying latent factors in multi-way data. This generalizes existing work on sparse tensor decomposition and penalized matrix decompositions, in a manner parallel to the generalized lasso for regression and smoothing problems. Our ap…
Paper introduces invariance-adapted latent space for contrastive learning.
problem Understanding the effectiveness of contrastive learning in data representation.
method Introduces invariance-adapted latent space and uses Lasso-type metric.
result Contrastive learning with Lasso-type metric can find an invariance-adapted latent space.
Paper develops a method for causal representation learning from irregular tensors.
problem Complex patterns in high-dimensional, irregular tensor data.
method Novel causal formulation and CaRTeD framework integrating temporal causal representation learning with irregular tensor decomposition.
result Framework provides theoretical guarantees and outperforms state-of-the-art techniques.
Topic models have achieved significant successes in analyzing large-scale text corpus. In practical applications, we are always confronted with the challenge of model selection, i.e., how to appropriately set the number of topics. Following recent advances in topic model inference via tensor decomposition, we make a fi…