Tensor variable elimination for plated factor graphs enables exact inference in models with repeated structure.
problem Efficient inference in models with repeated structure.
method Generalized variable elimination to tensor variable elimination on plated factor graphs.
result Tractable inference for a class of plated factor graphs.
Functional tensors unify probabilistic programming with automatic differentiation.
problem Designing probabilistic programming systems that can handle diverse inference strategies.
method Introducing functional tensors that capture benefits of tensors and continuous probability distributions.
result Functional tensors enable parallel exact inference for various modeling motifs.
Probabilistic graphical models offer a powerful framework to account for the dependence structure between variables, which is represented as a graph. However, the dependence between variables may render inference tasks intractable. In this paper we review techniques exploiting the graph structure for exact inference, b…
Introduces tensor bandits for multi-dimensional online decision making.
problem Optimal decision making in multi-dimensional online scenarios.
method Stochastic low-rank tensor bandits, tensor elimination, tensor epoch-greedy, tensor ensemble sampling.
result Tensor elimination and tensor epoch-greedy algorithms outperform existing methods.
SurvNet selects important variables in DNNs with false discovery rate control.
problem Variable selection in deep neural networks (DNNs) for interpretability.
method Backward elimination procedure based on a new variable importance measure.
result SurvNet estimates and controls false discovery rate of selected variables.
OGRe simplifies tensor calculations in general relativity.
problem Complex tensor calculations in general relativity.
method Object-oriented design for tensor calculus, automatic transformations, and optimized algorithms.
result Eliminates user errors and simplifies tensor calculations.
Probabilistic graphical models are a key tool in machine learning applications. Computing the partition function, i.e., normalizing constant, is a fundamental task of statistical inference but it is generally computationally intractable, leading to extensive study of approximation methods. Iterative variational methods…
New method simplifies optimization landscapes by transforming saddle points.
problem Saddle points hinder non-convex optimization in machine learning.
method Variable elimination algorithms, like VarPro, are compared to reveal geometric insights.
result Variable elimination reshapes critical point structure, creating local maxima from saddle points.
A new variable importance measure for DRFs detects broader impacts on output distributions.
problem Estimating full conditional distributions of multivariate outputs given inputs.
method Based on the drop and relearn principle and MMD distance.
result Consistent and high-performing variable importance measure for DRFs.
A tensor field generates separation of variables for certain metrics.
problem Finding metrics with specific tensor field properties.
method Constructing differential invariants for a (1,1)-tensor field. result Explicit system of invariants for metrics generating separation of variables.
SGD recovers multiple signal vectors in noisy tensor PCA.
problem Estimating multiple signal vectors from noisy tensor observations.
method Online stochastic gradient descent (SGD) in high dimensions with detailed analysis of correlations.
result Sequential elimination of correlations allows recovery of all spikes from Np−2 samples. Method eliminates nuisance functions for spatially varying causal effects.
problem Inferring causal effects in presence of spatial confounding.
method Eliminates nuisance functions, mitigates errors-in-variables.
result Robust and accurate inference of spatially varying heterogeneous causal effects.
Probabilistic inference in graphical models is the task of computing marginal and conditional densities of interest from a factorized representation of a joint probability distribution. Inference algorithms such as variable elimination and belief propagation take advantage of constraints embedded in this factorization …
We formulate and solve a tensor model using a latent-variable approach.
problem Parameter inference for Poisson canonical polyadic tensor models.
method Latent-variable formulation, Expectation-Maximization algorithms, Fisher information matrices.
result Derivation of Fisher information for PCP models, insights into model well-posedness.
Safe screening rules reduce ℓ0-regression computation by fixing 76% of variables.
problem Efficiently solving ℓ0-regression problems with large datasets. method Convex relaxation and safe screening rules to eliminate variables.
result 76% of variables can be fixed to their optimal values, reducing computational burden.
Develops methods to estimate high rank tensors from noisy data.
problem Estimating high rank tensors from noisy observations.
method Generative latent variable tensor model, polynomial-time spectral algorithm.
result Achieves computationally optimal rate for signal tensor estimation.
tvGP-VAE models tensor-valued latent variables with Gaussian processes for better data structure representation.
problem Agnostic latent variables in VAEs ignore data structure correlations.
method Proposes tensor-variate Gaussian process prior for variational autoencoder.
result Explicitly modeling correlation structures improves model performance in reconstruction.
Paper generalizes tensor-train approximation for complex random variables.
problem Characterizing intractable high-dimensional random variables.
method Extends inverse Rosenblatt transform to general reference measures and integrates into deep variable transformation framework.
result Deep inverse Rosenblatt transport significantly expands tensor approximations for complex random variables.
Tensor-based method simplifies causal skeleton discovery.
problem Discover causal relationships between variables.
method Express associations as tensors to reduce dimensionality.
result Causal skeleton can be determined using pair-wise tensors.
Efficiently recovers low-tubal-rank tensors from few measurements.
problem Recovering tensors with low tubal-rank from limited measurements.
method Factorization and factorized gradient descent.
result Factorized gradient descent reduces computational costs and storage requirements.
New concentration inequalities for tensors with heavy-tailed coefficients.
problem Developing bounds for Euclidean functions of tensors with sub-Weibull distributions.
method Extending concentration inequalities to sub-Weibull random tensors, using new inequalities for heavy-tailed random variables and martingale analysis.
result Established a phase transition between sub-gaussian and heavy-tailed regimes for Euclidean functions of tensors.
A new method for decomposing non-negative tensors using energy-based modeling.
problem Challenges in traditional tensor decomposition methods, especially global optimization and rank selection.
method Energy-based modeling of tensors, considering interactions between modes for global optimization.
result Demonstrates effectiveness in tensor completion and approximation, revealing a relationship between many-body and low-rank approximations.
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…
We present a novel analysis of the dynamics of tensor power iterations in the overcomplete regime where the tensor CP rank is larger than the input dimension. Finding the CP decomposition of an overcomplete tensor is NP-hard in general. We consider the case where the tensor components are randomly drawn, and show that …
TSCD is an algorithm for causal discovery using second-order statistics.
problem Causal discovery
method Tensor-based Second-order Causal Discovery (TSCD)
result Identifiable causal order and parameters from logarithmic number of interventions
Shapley value improves model interpretation but not causal inference.
problem Improving model interpretability without losing predictive power.
method Analyzed Shapley value in Bayesian networks, linking it to conditional independence.
result Eliminating high Shapley value variables does not harm predictive performance, but low Shapley value variables can.
Paper introduces online tensor inference for real-time data analysis.
problem Real-time processing of high-dimensional tensor data.
method Stochastic Gradient Descent (SGD) for efficient online inference.
result Establishes non-asymptotic convergence and optimal estimation error rate.
Simplified KR polynomial for bipartite links reduces to tensor products of vector spaces.
problem Complexity reduction of Khovanov-Rozansky polynomial for bipartite links.
method Local reduction of matrix factorizations to planar cycles and simplification to vector spaces.
result KR polynomial for bipartite links simplifies to tensor products of vector spaces.
Paper proposes a transfer learning framework for tensor Gaussian graphical models.
problem Pooling heterogeneous tensor data for improved estimation and variable selection.
method Transfer learning framework that uses data-adaptive weights from auxiliary domains.
result Significant improvement in estimation errors and variable selection consistency.
A new tree method for tensor data improves regression accuracy.
problem Efficiently modeling tensor data for regression problems.
method Scalar-output regression tree models for scalar-on-tensor problems, and tensor-on-tensor problems using additive tree ensemble approaches.
result The tensor-input tree (TT) method outperforms tensor-input GP models in efficiency and accuracy.
This paper explores the following question: what kind of statistical guarantees can be given when doing variable selection in high-dimensional models? In particular, we look at the error rates and power of some multi-stage regression methods. In the first stage we fit a set of candidate models. In the second stage we s…
Constructs orthogonal coordinates in curved spaces.
problem Separating variables in curved spaces.
method Explicit construction of orthogonal coordinates and transformations.
result Explicit formulas for Killing tensors and Stäckel matrices.
Spectral methods have greatly advanced the estimation of latent variable models, generating a sequence of novel and efficient algorithms with strong theoretical guarantees. However, current spectral algorithms are largely restricted to mixtures of discrete or Gaussian distributions. In this paper, we propose a kernel m…
Derives derivatives and geometric framework for functions with non-independent variables.
problem Characterizing functions with non-independent variables in probabilistic models.
method Derives actual and dependent partial derivatives, dependent Jacobian matrix, and tensor metric.
result Derives gradient, Hessian, and Taylor expansion for functions with non-independent variables.
A new metric tensor improves Riemann manifold Monte Carlo for Bayesian models.
problem Improving sampling efficiency in Bayesian hierarchical models.
method Metric tensor derived from log-density gradient covariance matrices.
result Metric tensors enhance sampling for complex Bayesian models.
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.
Proposes a method to reveal nonlinearities in tensor data.
problem Capturing nonlinear relationships in high-dimensional tensor data.
method Linear tensor projection method to maximize prediction accuracy.
result Effective in revealing nonlinear relationships in tensor data.
We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical Gaussian mixtures, ICA, and sparse coding models. We provide tight concentration…
Study homogenizes equations on parallelizable manifolds using tensor localization and periodicity.
problem Homogenizing oscillating linear elliptic equations on parallelizable manifolds.
method Two-scale convergence through localization and periodicity induced by geometry.
result Explicit cell formulae for the homogenization limit and a theory of two-scale convergence of tensors.
A new tensor decomposition method for fMRI data captures both spatial and temporal variability.
problem Challenges in modeling shared and subject-specific structure in multisubject spatiotemporal data, especially in neuroimaging.
method Introduces a spatiotemporal variational tensor decomposition (ST-VTD) framework combining tensor factorization with structured priors for flexible representation of spatial and temporal dynamics.
result Significantly improves latent factor recovery in fMRI data compared to classical and probabilistic decomposition benchmarks.
In this article we show the duality between tensor networks and undirected graphical models with discrete variables. We study tensor networks on hypergraphs, which we call tensor hypernetworks. We show that the tensor hypernetwork on a hypergraph exactly corresponds to the graphical model given by the dual hypergraph. …
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…
Many machine learning applications use latent variable models to explain structure in data, whereby visible variables (= coordinates of the given datapoint) are explained as a probabilistic function of some hidden variables. Finding parameters with the maximum likelihood is NP-hard even in very simple settings. In rece…
The current study proposes a dimension reduction method, stepwise support vector machine (SVM), to reduce the dimensions of large p small n datasets. The proposed method is compared with other dimension reduction methods, namely, the Pearson product difference correlation coefficient (PCCs), recursive feature eliminati…
Efficiently evaluate generative models at the prompt level using tensor factorization.
problem Fine-grained evaluations of generative models are costly and often misaligned with human judgment.
method Tensor factorization model that merges cheap autorater data with a small set of human gold-standard labels.
result The method provides accurate and tight confidence intervals for model performance.
Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data. However, the standard assumption is that we have sufficient data to estimate these moments to high accuracy. In this work, we consider the case in which certain dimensions of the data are not always …
New method selects features via tensor decomposition and submodular optimization.
problem Feature selection for high-dimensional data.
method Low-rank tensor model, submodular optimization, greedy algorithm.
result Proposed method outperforms state-of-the-art feature selection.
New framework extends ICA for non-independent variables, identifying pairwise mean independence.
problem Non-independent variables complicating ICA recovery.
method Algebraic recovery algorithm based on least-squares optimization over the orthogonal group.
result Pairwise mean independence is identifiable, robust to independence constraints.