Difference between revisions of "SOCR News ISS JSM 2025"
(→Session Logistics) |
|||
| Line 38: | Line 38: | ||
Title: ''Probabilistic Symmetry, Variable Exchangeability, and Deep Network Learning Invariance and Equivariance''. | Title: ''Probabilistic Symmetry, Variable Exchangeability, and Deep Network Learning Invariance and Equivariance''. | ||
| − | : This talk will first describe the mathematical-statistics framework for representing, modeling, and utilizing invariance and equivariance properties of deep neural networks. By drawing direct parallels between characterizations of invariance and equivariance principles, probabilistic symmetry, and statistical inference, we explore the foundational properties underpinning reliability in deep learning models. We examine the group-theoretic invariance in a number of deep neural networks including, multilayer perceptrons, convolutional networks, transformers, variational autoencoders, and steerable neural networks. | + | : This talk will first describe the mathematical-statistics framework for representing, modeling, and utilizing invariance and equivariance properties of deep neural networks. By drawing direct parallels between characterizations of invariance and equivariance principles, probabilistic symmetry, and statistical inference, we explore the foundational properties underpinning reliability in deep learning models. We examine the group-theoretic invariance in a number of deep neural networks including, multilayer perceptrons, convolutional networks, transformers, variational autoencoders, and steerable neural networks. Understanding the theoretical foundation underpinning deep neural network invariance is critical for reliable estimation of prior-predictive distributions, accurate calculations of posterior inference, and consistent AI prediction, classification, and forecasting. Two relevant data studies will be presented: one is on a theoretical physics dataset, the other is on an fMRI music dataset. Some biomedical and imaging applications are discussed at the end. |
| − | Understanding the theoretical foundation underpinning deep neural network invariance is critical for reliable estimation of prior-predictive distributions, accurate calculations of posterior inference, and consistent AI prediction, classification, and forecasting. Two relevant data studies will be presented: one is on a theoretical physics dataset, the other is on an fMRI music dataset. Some biomedical and imaging applications are discussed at the end. | ||
| − | === [https://sites.google.com/view/changbozhu/home Changbo Zhu, University of Notre Dame] and Jane-Ling Wang, University of California-Davis | + | === [https://sites.google.com/view/changbozhu/home Changbo Zhu, University of Notre Dame] and Jane-Ling Wang, University of California-Davis=== |
Title: ''Testing independence for sparse longitudinal data'' | Title: ''Testing independence for sparse longitudinal data'' | ||
: With the advance of science and technology, more and more data are collected in the form of functions. A fundamental question for a pair of random functions is to test whether they are independent. This problem becomes quite challenging when the random trajectories are sampled irregularly and sparsely for each subject. In other words, each random function is only sampled at a few time-points, and these time-points vary with subjects. Furthermore, the observed data may contain noise. To the best of our knowledge, there exists no consistent test in the literature to test the independence of sparsely observed functional data. We show in this work that testing pointwise independence simultaneously is feasible. The test statistics are constructed by integrating pointwise distance covariances (Székely et al., 2007) and are shown to converge, at a certain rate, to their corresponding population counterparts, which characterize the simultaneous pointwise independence of two random functions. The performance of the proposed methods is further verified by Monte Carlo simulations and analysis of real data. | : With the advance of science and technology, more and more data are collected in the form of functions. A fundamental question for a pair of random functions is to test whether they are independent. This problem becomes quite challenging when the random trajectories are sampled irregularly and sparsely for each subject. In other words, each random function is only sampled at a few time-points, and these time-points vary with subjects. Furthermore, the observed data may contain noise. To the best of our knowledge, there exists no consistent test in the literature to test the independence of sparsely observed functional data. We show in this work that testing pointwise independence simultaneously is feasible. The test statistics are constructed by integrating pointwise distance covariances (Székely et al., 2007) and are shown to converge, at a certain rate, to their corresponding population counterparts, which characterize the simultaneous pointwise independence of two random functions. The performance of the proposed methods is further verified by Monte Carlo simulations and analysis of real data. | ||
| + | |||
| + | === Other relevant sessions/talks=== | ||
| + | |||
| + | * [https://ww3.aievolution.com/JSMAnnual2025/Events/viewEv?ev=4612 A Bayesian Multiplex Graph Classifier of Functional Brain Connectivity Across Cognitive Tasks] | ||
| + | |||
| + | : This work seeks to investigate the impact of aging on functional connectivity across different cognitive control scenarios, particularly emphasizing the identification of brain regions significantly associated with early aging. By conceptualizing functional connectivity within each cognitive control scenario as a graph, with brain regions as nodes, the statistical challenge revolves around devising a regression framework to predict a binary scalar outcome (aging or normal) using multiple graph predictors. To address this challenge, we propose the Bayesian Multiplex Graph Classifier (BMGC). Accounting for multiplex graph topology, our method models edge coefficients at each graph layer using bilinear interactions between the latent effects associated with the two nodes connected by the edge. This approach also employs a variable selection framework on node-specific latent effects from all graph layers to identify influential nodes linked to observed outcomes. Crucially, the proposed framework is computationally efficient and quantifies the uncertainty in node identification, coefficient estimation, and binary outcome prediction. | ||
| + | |||
| + | : Presenter: Jose Rodriguez-Acosta, Texas A&M University, co authors, Sharmistha Guha, Texas A&M University, and Ivo Dinov, Statistics Online Computational Resource (Michigan) | ||
<hr> | <hr> | ||
{{translate|pageName=https://wiki.socr.umich.edu/index.php?title=SOCR_News_ISS_JSM_2025}} | {{translate|pageName=https://wiki.socr.umich.edu/index.php?title=SOCR_News_ISS_JSM_2025}} | ||
Revision as of 17:51, 2 April 2025
Contents
[hide]SOCR News & Events: 2025 Joint Statistical Meeting, Nashville, TN
The 2025 Joint Statistical Meeting (JSM) will take place August 2-7, 2025 in Nashville, TN. The annual event will feature an invited special session entitled Statistical Inference and AI Modeling of High-Dimensional Longitudinal Data.
Session Logistics
- Title: Statistical Inference and AI Modeling of High-Dimensional Longitudinal Data
- Organizer: Ivo Dinov (Michigan)
- Chair: Chunming Zhang, University of Wisconsin-Madison
- Speakers: Changbo Zhu, University of Notre Dame, Yi Zhao, Indiana University, and Yueyang Shen (Michigan)
- Discussant: Ivo Dinov (Michigan), Statistics Online Computational Resource (SOCR)
- Date/Time: 8/5/2025, 2:00-3:00 PM US ET
- Venue: Music City Center, 201 Rep. John Lewis Way South, Nashville, TN 37203, map and parking.
- Registration: 2025 JSM Registration (starts May 1, 2025)
- Conference: 2025 Joint Statistical Meeting (JSM)
- Format: podium-presentations (lectures)
Sponsors
- Section on Statistics in Imaging
- International Association for Statistical Computing
- International Statistical Institute
Session Description
In support of the for JSM 2025 theme, "Statistics, Data Science, and Al Enriching Society," this invited special session will bring together a diverse group of academic researchers, each contributing to the cutting-edge intersections of statistical learning methods, Al applications, and high-dimensional data analysis.
In this session, Changbo Zhu, Yi Zhao, and Yueyang Shen will present cutting-edge methodologies that harness the power of statistical learning, topological modeling, and deep learning to advance the analysis of complex, high-dimensional spatiotemporal data in various scientific domains. Speakers will demonstrate topological methods for handling challenges related to neuroimaging data complexity and scale and provide new perspectives on brain connectivity and function. Recent work on longitudinal and covariance regression in high-dimensional data will expose temporal structures involving a large number of covariates. The topics will cover deep learning invariance and equivariance, which characterize the robustness and generalizability of various AI models in real-world applications. All talks will emphasize challenges and opportunities in statistical and Al techniques to extract meaningful unbiased insights from complex data. This session aligns with the overarching conference theme "Statistics, Data Science, and Al Enriching Society" and will highlight applications in neuroscience, longitudinal studies, and AI forecasting, and trustworthy decision-making.
Yi Zhao (Indiana University)
Title: "Longitudinal regression of covariance matrix outcomes", addressing the challenges and methodologies for analyzing data with both temporal and complex covariate structures.
- In this study, a longitudinal regression model for covariance matrix outcomes is introduced. The proposal considers a multilevel generalized linear model for regressing covariance matrices on (time-varying) predictors. This model simultaneously identifies covariate-associated components from covariance matrices, estimates regression coefficients, and captures the within-subject variation in the covariance matrices. Optimal estimators are proposed for both low-dimensional and high-dimensional cases by maximizing the (approximated) hierarchical-likelihood function. These estimators are proved to be asymptotically consistent, where the proposed covariance matrix estimator is the most efficient under the low-dimensional case and achieves the uniformly minimum quadratic loss among all linear combinations of the identity matrix and the sample covariance matrix under the high-dimensional case. Through extensive simulation studies, the proposed approach achieves good performance in identifying the covariate-related components and estimating the model parameters. Applying to a longitudinal resting-state functional magnetic resonance imaging data set from the Alzheimer's Disease (AD) Neuroimaging Initiative, the proposed approach identifies brain networks that demonstrate the difference between males and females at different disease stages. The findings are in line with existing knowledge of AD and the method improves the statistical power over the analysis of cross-sectional data.
Yueyang Shen (University of Michigan)
Title: Probabilistic Symmetry, Variable Exchangeability, and Deep Network Learning Invariance and Equivariance.
- This talk will first describe the mathematical-statistics framework for representing, modeling, and utilizing invariance and equivariance properties of deep neural networks. By drawing direct parallels between characterizations of invariance and equivariance principles, probabilistic symmetry, and statistical inference, we explore the foundational properties underpinning reliability in deep learning models. We examine the group-theoretic invariance in a number of deep neural networks including, multilayer perceptrons, convolutional networks, transformers, variational autoencoders, and steerable neural networks. Understanding the theoretical foundation underpinning deep neural network invariance is critical for reliable estimation of prior-predictive distributions, accurate calculations of posterior inference, and consistent AI prediction, classification, and forecasting. Two relevant data studies will be presented: one is on a theoretical physics dataset, the other is on an fMRI music dataset. Some biomedical and imaging applications are discussed at the end.
Changbo Zhu, University of Notre Dame and Jane-Ling Wang, University of California-Davis
Title: Testing independence for sparse longitudinal data
- With the advance of science and technology, more and more data are collected in the form of functions. A fundamental question for a pair of random functions is to test whether they are independent. This problem becomes quite challenging when the random trajectories are sampled irregularly and sparsely for each subject. In other words, each random function is only sampled at a few time-points, and these time-points vary with subjects. Furthermore, the observed data may contain noise. To the best of our knowledge, there exists no consistent test in the literature to test the independence of sparsely observed functional data. We show in this work that testing pointwise independence simultaneously is feasible. The test statistics are constructed by integrating pointwise distance covariances (Székely et al., 2007) and are shown to converge, at a certain rate, to their corresponding population counterparts, which characterize the simultaneous pointwise independence of two random functions. The performance of the proposed methods is further verified by Monte Carlo simulations and analysis of real data.
Other relevant sessions/talks
- This work seeks to investigate the impact of aging on functional connectivity across different cognitive control scenarios, particularly emphasizing the identification of brain regions significantly associated with early aging. By conceptualizing functional connectivity within each cognitive control scenario as a graph, with brain regions as nodes, the statistical challenge revolves around devising a regression framework to predict a binary scalar outcome (aging or normal) using multiple graph predictors. To address this challenge, we propose the Bayesian Multiplex Graph Classifier (BMGC). Accounting for multiplex graph topology, our method models edge coefficients at each graph layer using bilinear interactions between the latent effects associated with the two nodes connected by the edge. This approach also employs a variable selection framework on node-specific latent effects from all graph layers to identify influential nodes linked to observed outcomes. Crucially, the proposed framework is computationally efficient and quantifies the uncertainty in node identification, coefficient estimation, and binary outcome prediction.
- Presenter: Jose Rodriguez-Acosta, Texas A&M University, co authors, Sharmistha Guha, Texas A&M University, and Ivo Dinov, Statistics Online Computational Resource (Michigan)
Translate this page:
