arXiv subjects

Steven Winter

Publications and source records attributed to Steven Winter.

5 recordsLinked to original sources

arXiv2023

Identifiable and interpretable nonparametric factor analysis

Factor models are widely used to reduce dimensionality in modeling high-dimensional data. However, there remains a need for models that can be reliably fit in modest sample sizes and are identifiable, interpretable, and flexible. To address this gap, we propose a NIFTY model that uses a linear factor structure with Gaussian residuals, but with a novel latent variable modeling structure. In particular, we model each latent variable as a one-dimensional nonlinear mapping of a uniform latent location. A key innovation is allowing different latent variables to be transformations of the same latent locations, accommodating intrinsic lower-dimensional nonlinear structures. Leveraging on pre-trained data obtained by diffusion maps and post-processing of MCMC samples, we obtain model identifiability. In addition, we softly constrain the empirical distribution of the latent locations to be close to uniform to address a latent posterior shift problem, which is common in factor models and can lead to substantial bias in parameter inferences, predictions, and generative modeling. We show good performance in density estimation and data visualization in simulations, and apply NIFTY to bird song data in an environmental monitoring application.

stat.ME↗

arXiv2023

Sequential Gibbs Posteriors with Applications to Principal Component Analysis

Gibbs posteriors are proportional to a prior distribution multiplied by an exponentiated loss function, with a key tuning parameter weighting information in the loss relative to the prior and providing a control of posterior uncertainty. Gibbs posteriors provide a principled framework for likelihood-free Bayesian inference, but in many situations, including a single tuning parameter inevitably leads to poor uncertainty quantification. In particular, regardless of the value of the parameter, credible regions have far from the nominal frequentist coverage even in large samples. We propose a sequential extension to Gibbs posteriors to address this problem. We prove the proposed sequential posterior exhibits concentration and a Bernstein-von Mises theorem, which holds under easy to verify conditions in Euclidean space and on manifolds. As a byproduct, we obtain the first Bernstein-von Mises theorem for traditional likelihood-based Bayesian posteriors on manifolds. All methods are illustrated with an application to principal component analysis.

stat.ME↗

arXiv2023

Machine Learning and the Future of Bayesian Computation

Bayesian models are a powerful tool for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty through the posterior distribution. Practical posterior computation is commonly performed via MCMC, which can be computationally infeasible for high dimensional models with many observations. In this article we discuss the potential to improve posterior computation using ideas from machine learning. Concrete future directions are explored in vignettes on normalizing flows, Bayesian coresets, distributed Bayesian inference, and variational inference.

stat.ML↗

arXiv2022

Interpretable AI for relating brain structural and functional connectomes

One of the central problems in neuroscience is understanding how brain structure relates to function. Naively one can relate the direct connections of white matter fiber tracts between brain regions of interest (ROIs) to the increased co-activation in the same pair of ROIs, but the link between structural and functional connectomes (SCs and FCs) has proven to be much more complex. To learn a realistic generative model characterizing population variation in SCs, FCs, and the SC-FC coupling, we develop a graph auto-encoder that we refer to as Staf-GATE. We trained Staf-GATE with data from the Human Connectome Project (HCP) and show state-of-the-art performance in predicting FC and joint generation of SC and FC. In addition, as a crucial component of the proposed approach, we provide a masking-based algorithm to extract interpretable inferences about SC-FC coupling. Our interpretation methods identified important SC subnetworks for FC coupling and relating SC and FC with sex.

q-bio.NC↗

arXiv2020

Multi-scale graph principal component analysis for connectomics

In brain connectomics, the cortical surface is parcellated into different regions of interest (ROIs) prior to statistical analysis. The brain connectome for each individual can then be represented as a graph, with the nodes corresponding to ROIs and edges to connections between ROIs. Such a graph can be summarized as an adjacency matrix, with each cell containing the strength of connection between a pair of ROIs. These matrices are symmetric with the diagonal elements corresponding to self-connections typically excluded. A major disadvantage of such representations of the connectome is their sensitivity to the chosen ROIs, including critically the number of ROIs and hence the scale of the graph. As the scale becomes finer and more ROIs are used, graphs become increasingly sparse. Clearly, the results of downstream statistical analyses can be highly dependent on the chosen parcellation. To solve this problem, we propose a multi-scale graph factorization, which links together scale-specific factorizations through a common set of individual-specific scores. These scores summarize an individual's brain structure combining information across measurement scales. We obtain a simple and efficient algorithm for implementation, and illustrate substantial advantages over single scale approaches in simulations and analyses of the Human Connectome Project dataset.

stat.ME↗