More Like this

1. Hybrid elicitation and quantile-parametrized likelihood

   https://doi.org/10.1007/s11222-023-10325-0  

   Perepolkin, Dmytro; Goodrich, Benjamin; Sahlin, Ullrika (February 2024, Statistics and Computing)

   Abstract This paper extends the application of quantile-based Bayesian inference to probability distributions defined in terms of quantiles of observable quantities. Quantile-parameterized distributions are characterized by high shape flexibility and parameter interpretability, making them useful for eliciting information about observables. To encode uncertainty in the quantiles elicited from experts, we propose a Bayesian model based on the metalog distribution and a variant of the Dirichlet prior. We discuss the resulting hybrid expert elicitation protocol, which aims to characterize uncertainty in parameters by asking questions about observable quantities. We also compare and contrast this approach with parametric and predictive elicitation methods. 

   more » « less
2. Ensemble‐Based Experimental Design for Targeting Data Acquisition to Inform Climate Models

   https://doi.org/10.1029/2022MS002997  

   Dunbar, Oliver R. A.; Howland, Michael F.; Schneider, Tapio; Stuart, Andrew M. (September 2022, Journal of Advances in Modeling Earth Systems)

   Abstract Data required to calibrate uncertain general circulation model (GCM) parameterizations are often only available in limited regions or time periods, for example, observational data from field campaigns, or data generated in local high‐resolution simulations. This raises the question of where and when to acquire additional data to be maximally informative about parameterizations in a GCM. Here we construct a new ensemble‐based parallel algorithm to automatically target data acquisition to regions and times that maximize the uncertainty reduction, or information gain, about GCM parameters. The algorithm uses a Bayesian framework that exploits a quantified distribution of GCM parameters as a measure of uncertainty. This distribution is informed by time‐averaged climate statistics restricted to local regions and times. The algorithm is embedded in the recently developed calibrate‐emulate‐sample framework, which performs efficient model calibration and uncertainty quantification with onlymodel evaluations, compared withevaluations typically needed for traditional approaches to Bayesian calibration. We demonstrate the algorithm with an idealized GCM, with which we generate surrogates of local data. In this perfect‐model setting, we calibrate parameters and quantify uncertainties in a quasi‐equilibrium convection scheme in the GCM. We consider targeted data that are (a) localized in space for statistically stationary simulations, and (b) localized in space and time for seasonally varying simulations. In these proof‐of‐concept applications, the calculated information gain reflects the reduction in parametric uncertainty obtained from Bayesian inference when harnessing a targeted sample of data. The largest information gain typically, but not always, results from regions near the intertropical convergence zone. 

   more » « less
3. Bayesian Pyramids: identifiable multilayer discrete latent structure models for discrete data

   https://doi.org/10.1093/jrsssb/qkad010  

   Gu, Yuqi; Dunson, David B (March 2023, Journal of the Royal Statistical Society Series B: Statistical Methodology)

   Abstract High-dimensional categorical data are routinely collected in biomedical and social sciences. It is of great importance to build interpretable parsimonious models that perform dimension reduction and uncover meaningful latent structures from such discrete data. Identifiability is a fundamental requirement for valid modeling and inference in such scenarios, yet is challenging to address when there are complex latent structures. In this article, we propose a class of identifiable multilayer (potentially deep) discrete latent structure models for discrete data, termed Bayesian Pyramids. We establish the identifiability of Bayesian Pyramids by developing novel transparent conditions on the pyramid-shaped deep latent directed graph. The proposed identifiability conditions can ensure Bayesian posterior consistency under suitable priors. As an illustration, we consider the two-latent-layer model and propose a Bayesian shrinkage estimation approach. Simulation results for this model corroborate the identifiability and estimatability of model parameters. Applications of the methodology to DNA nucleotide sequence data uncover useful discrete latent features that are highly predictive of sequence types. The proposed framework provides a recipe for interpretable unsupervised learning of discrete data and can be a useful alternative to popular machine learning methods. 

   more » « less
4. A Bayesian Approach to Modeling Unit Manufacturing Process Environmental Impacts using Limited Data with Case Studies on Laser Powder Bed Fusion Cumulative Energy Demand

   Liao, Jiankan; Huan, Xun; Haapala, Karl; Cooper, Daniel (May 2023, Procedia CIRP)

   Informed decision-making for sustainable manufacturing requires accurate manufacturing process environmental impact models with uncertainty quantification (UQ). For emerging manufacturing technologies, there is often insufficient process data available to derive accurate data-driven models. This paper explores an alternative mechanistic modeling approach using easy-to-access data from a given machine to perform Bayesian inference and reduce the uncertainty of model parameters. First, we derive mechanistic models of the cumulative energy demand (CED) for making aluminum (AlSi10) and nylon (PA12) parts using laser powder bed fusion (L-PBF). Initial parametric uncertainty is assigned to the model inputs informed by literature reviews and interviews with industry experts. Second, we identify the most critical sources of uncertainty using variance-based global sensitivity analyses; therefore, reducing the dimension of the problem. For metal and polymer L-PBF, critical uncertainty is related to the adiabatic efficiency of the process (a measure of the efficiency with which the laser energy is used to fuse the powder) and the recoating time per layer between laser scans. Data pertinent to both of these parameters include the part geometry (height and volume) and total build time. Between three and eight data points on part geometry and build time were collected on two different L-PBF machines and Bayesian inference was performed to reduce the uncertainty of the adiabatic efficiency and recoating time per layer on each machine. This approach was validated by subsequently taking direct parameter measurements on these machines during operation. The delivered electricity uncertainty is reduced by 40-70% after performing inference, highlighting the potential to construct accurate energy and environmental impact models of manufacturing processes using small easy-to-access datasets without interfering with the operations of the manufacturing facility. 

   more » « less
5. Graph Structure Learning with Interpretable Bayesian Neural Networks

   Wasserman, Max; Mateos, Gonzalo (September 2024, Transactions on machine learning research)

   Graphs serve as generic tools to encode the underlying relational structure of data. Often this graph is not given, and so the task of inferring it from nodal observations becomes important. Traditional approaches formulate a convex inverse problem with a smoothness promoting objective and rely on iterative methods to obtain a solution. In supervised settings where graph labels are available, one can unroll and truncate these iterations into a deep network that is trained end-to-end. Such a network is parameter efficient and inherits inductive bias from the optimization formulation, an appealing aspect for data constrained settings in, e.g., medicine, finance, and the natural sciences. But typically such settings care equally about \textit{uncertainty} over edge predictions, not just point estimates. Here we introduce novel iterations with independently interpretable parameters, i.e., parameters whose values - independent of other parameters' settings - proportionally influence characteristics of the estimated graph, such as edge sparsity. After unrolling these iterations, prior knowledge over such graph characteristics shape prior distributions} over these independently interpretable network parameters to yield a Bayesian neural network (BNN) capable of graph structure learning (GSL) from smooth signal observations. Fast execution and parameter efficiency allow for high-fidelity posterior approximation via Markov Chain Monte Carlo (MCMC) and thus uncertainty quantification on edge predictions. Informative priors unlock modeling tools from Bayesian statistics like prior predictive checks. Synthetic and real data experiments corroborate this model's ability to provide well-calibrated estimates of uncertainty, in test cases that include unveiling economic sector modular structure from S&P500 data and recovering pairwise digit similarities from MNIST images. Overall, this framework enables GSL in modest-scale applications where uncertainty on the data structure is paramount 

   more » « less