skip to main content


Title: VarFA: {A} Variational Factor Analysis Framework For Efficient Bayesian Learning Analytics
We propose VarFA, a variational inference factor analysis framework that extends existing factor analysis models for educational data mining to efficiently output uncertainty estimation in the model's estimated factors. Such uncertainty information is useful, for example, for an adaptive testing scenario, where additional tests can be administered if the model is not quite certain about a students' skill level estimation. Traditional Bayesian inference methods that produce such uncertainty information are computationally expensive and do not scale to large data sets. VarFA utilizes variational inference which makes it possible to efficiently perform Bayesian inference even on very large data sets. We use the sparse factor analysis model as a case study and demonstrate the efficacy of VarFA on both synthetic and real data sets. VarFA is also very general and can be applied to a wide array of factor analysis models.  more » « less
Award ID(s):
1631556
NSF-PAR ID:
10211596
Author(s) / Creator(s):
; ; ;
Editor(s):
Rafferty, A.; Whitehall, J.; Cristobal, R.; Cavalli-Sforza, V.
Date Published:
Journal Name:
Proceedings of the 13th International Conference on Educational Data Mining
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Multivariate spatially oriented data sets are prevalent in the environmental and physical sciences. Scientists seek to jointly model multiple variables, each indexed by a spatial location, to capture any underlying spatial association for each variable and associations among the different dependent variables. Multivariate latent spatial process models have proved effective in driving statistical inference and rendering better predictive inference at arbitrary locations for the spatial process. High‐dimensional multivariate spatial data, which are the theme of this article, refer to data sets where the number of spatial locations and the number of spatially dependent variables is very large. The field has witnessed substantial developments in scalable models for univariate spatial processes, but such methods for multivariate spatial processes, especially when the number of outcomes are moderately large, are limited in comparison. Here, we extend scalable modeling strategies for a single process to multivariate processes. We pursue Bayesian inference, which is attractive for full uncertainty quantification of the latent spatial process. Our approach exploits distribution theory for the matrix‐normal distribution, which we use to construct scalable versions of a hierarchical linear model of coregionalization (LMC) and spatial factor models that deliver inference over a high‐dimensional parameter space including the latent spatial process. We illustrate the computational and inferential benefits of our algorithms over competing methods using simulation studies and an analysis of a massive vegetation index data set.

     
    more » « less
  2. Rogers, Rebekah (Ed.)
    Abstract The ongoing global pandemic has sharply increased the amount of data available to researchers in epidemiology and public health. Unfortunately, few existing analysis tools are capable of exploiting all of the information contained in a pandemic-scale data set, resulting in missed opportunities for improved surveillance and contact tracing. In this paper, we develop the variational Bayesian skyline (VBSKY), a method for fitting Bayesian phylodynamic models to very large pathogen genetic data sets. By combining recent advances in phylodynamic modeling, scalable Bayesian inference and differentiable programming, along with a few tailored heuristics, VBSKY is capable of analyzing thousands of genomes in a few minutes, providing accurate estimates of epidemiologically relevant quantities such as the effective reproduction number and overall sampling effort through time. We illustrate the utility of our method by performing a rapid analysis of a large number of SARS-CoV-2 genomes, and demonstrate that the resulting estimates closely track those derived from alternative sources of public health data. 
    more » « less
  3. Abstract

    Joint modeling of spatially oriented dependent variables is commonplace in the environmental sciences, where scientists seek to estimate the relationships among a set of environmental outcomes accounting for dependence among these outcomes and the spatial dependence for each outcome. Such modeling is now sought for massive data sets with variables measured at a very large number of locations. Bayesian inference, while attractive for accommodating uncertainties through hierarchical structures, can become computationally onerous for modeling massive spatial data sets because of its reliance on iterative estimation algorithms. This article develops a conjugate Bayesian framework for analyzing multivariate spatial data using analytically tractable posterior distributions that obviate iterative algorithms. We discuss differences between modeling the multivariate response itself as a spatial process and that of modeling a latent process in a hierarchical model. We illustrate the computational and inferential benefits of these models using simulation studies and analysis of a vegetation index data set with spatially dependent observations numbering in the millions.

     
    more » « less
  4. Abstract

    Recent advances in deep learning for neural networks with large numbers of parameters have been enabled by automatic differentiation, an algorithmic technique for calculating gradients of measures of model fit with respect to model parameters. Estimation of high‐dimensional parameter sets is an important problem within the hydrological sciences. Here, we demonstrate the effectiveness of gradient‐based estimation techniques for high‐dimensional inverse estimation problems using a conceptual rainfall‐runoff model. In particular, we compare the effectiveness of Hamiltonian Monte Carlo and automatic differentiation variational inference against two nongradient‐dependent methods, random walk Metropolis and differential evolution Metropolis. We show that the former two techniques exhibit superior performance for inverse estimation of daily rainfall values and are much more computationally efficient on larger data sets in an experiment with synthetic data. We also present a case study evaluating the effectiveness of automatic differentiation variational inference for inverse estimation over 25 years of daily precipitation conditional on streamflow observations at three catchments and show that it is scalable to very high dimensional parameter spaces. The presented results highlight the power of combining hydrological process‐based models with optimization techniques from deep learning for high‐dimensional estimation problems.

     
    more » « less
  5. Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions. Meanwhile, another relevant but very different question remains yet open: how to model and quantify the uncertainty of an optimization algorithm (a.k.a., optimizer) itself? To close such a gap, the prerequisite is to consider the optimizers as sampled from a distribution, rather than a few prefabricated and fixed update rules. We first take the novel angle to consider the algorithmic space of optimizers, and provide definitions for the optimizer prior and likelihood, that intrinsically determine the posterior and therefore uncertainty. We then leverage the recent advance of learning to optimize (L2O) for the space parameterization, with the end-to-end training pipeline built via variational inference, referred to as uncertainty-aware L2O (UA-L2O). Our study represents the first effort to recognize and quantify the uncertainty of the optimization algorithm. The extensive numerical results show that, UA-L2O achieves superior uncertainty calibration with accurate confidence estimation and tight confidence intervals, suggesting the improved posterior estimation thanks to considering optimizer uncertainty. Intriguingly, UA-L2O even improves optimization performances for two out of three test functions, the loss function in data privacy attack, and four of five cases of the energy function in protein docking. Our codes are released at https://github.com/Shen-Lab/Bayesian-L2O. 
    more » « less