To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca

Abstract: Probabilistic models describe complex data generating processes and have been applied to a broad range of fields, such as epidemiology, pharmacology, and astrophysics. Inference for probabilistic models poses significant computational challenges, particularly as models grow in complexity and datasets increase in size. Modern hardware, with its parallelization capabilities, offers new opportunities to accelerate statistical inference. However, many traditional methods are not inherently designed for parallel computation. Markov chain Monte Carlo (MCMC), for instance, typically relies on a few long-running chains. I propose an alternative approach: running hundreds or thousands of shorter chains in parallel. To support this paradigm, I introduce the nested “R-hat,” a novel convergence diagnostic tailored for the many-short-chains regime, paving the way for faster and more automated MCMC.

Next I examine variational inference (VI). VI already leverages the parallelization capacities of modern hardware, however it lacks the theoretical guarantees of MCMC and other statistical methods. I present two key theoretical results: (1) a positive result demonstrating that VI can effectively learn symmetries even under misspecified approximations, and (2) a negative result revealing that factorized (or mean-field) approximations lead to an impossibility theorem, preventing the simultaneous estimation of multiple measures of uncertainty . These findings provide practical guidance for selecting VI’s objective function and approximation family, offering a path toward robust and scalable inference.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca

Abstract: AI/ML applications have quickly gained popularity in many scientific domains, and in some cases, even started replacing conventional approaches for data collection. However, the reliability of scientific findings purely based on ML-derived outcomes remains largely unexplored. In this talk, I will demonstrate that genetic association analysis based on ML-derived phenotypic outcomes can lead to pervasive false-positive findings. To address this, I will introduce a statistical framework named “POP-GWAS” for ML-assisted statistical inference for genetic discovery. It ensures valid and efficient inference given arbitrary "black-box" ML prediction. Moreover, the framework only requires summary statistics as input, enabling computationally efficient application at the biobank scale. Using POP-GWAS, I performed the largest genome-wide association study (GWAS) to date on bone mineral density derived from dual-energy X-ray absorptiometry imaging at 14 skeletal sites, achieving a 9.7%-50.7% gain in effective sample size compared to conventional approaches. This new approach identified 89 novel genetic associations and many complex traits showing significant skeletal-site- specific genetic correlations with bone mineral density. In addition, I will discuss the extension of this framework to general statistical tasks, providing both theoretical insights on statistical optimality and practical implications of summary-statistics-based statistical inference. Finally, I will give a brief overview of my research program, covering topics from quantifying gene-environment interactions to advanced genetic risk prediction in diverse ancestries.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca

Abstract: With the ubiquity of data, linking data sets has become crucial for myriad applications including healthcare, official statistics, ecology, fraud detection, and national security. Record linkage is the task of resolving duplicates in two or more partially overlapping sets of records, or files, from noisy data sources without a unique identifier. In any field where multiple sources of messy data are available to address a scientific problem, record linkage is a critical step in the analysis pipeline. In streaming record linkage, files arrive sequentially in time and estimates of the linkage structure are updated after the arrival of each file. The challenge in streaming record linkage is to efficiently update parameter estimates as new data arrive. In this talk, I present the first multi-file Bayesian record linkage model formulated specifically for the streaming data context. This model is fit using recursive updates, incorporating each new batch of data into the model parameters' posterior distribution. A novel Markov chain Monte Carlo algorithm is presented that performs recursive Bayesian updates while avoiding the issue of degradation, common to many recursive algorithms. This sampler achieves near-equivalent posterior inference to non-streaming algorithms at a small fraction of the compute time.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: In this talk, I will introduce PrairieLearn, an open-source platform designed for creating assessments with powerful randomization and autograding features. I will highlight why PrairieLearn is an ideal choice for courses in computer science, data science, and statistics. Additionally, I will demonstrate our tools for migrating questions from Canvas, building question banks, and generating test files for coding questions—offering practical advice for transitioning to PrairieLearn. Finally, I will provide a brief tutorial on creating assessments and questions using R or Python.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: The Killer Whale is the world’s largest predator and a cultural icon in the Pacific Northwest. In the past two decades, the Southern Resident Killer Whale population has declined by more than 25 percent, putting the population at risk of extinction. Much of the whale’s habitat in our local waters overlaps with the shipping lanes that connect the Pacific Ocean with ports in southern British Columbia and northern Washington State. The continued decline in SRKW has been linked to disturbance from commercial vessels servicing our regional ports. In recent years, citizen science networks connected through social media are providing real-time sighting information while substantial infrastructure investment has resulted in real-time underwater acoustic monitoring stations. This has opened the possibility of forecasting systems to fuse these real-time data streams with movement models to predict future trajectories of whales. This seminar will present recent progress in building the A.I. detection/classification algorithms, real-time movement models, and computing infrastructure for real-time mitigation of commercial vessel impacts within SRKW critical habitat.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: Model selection in Gaussian processes scales prohibitively with the size of the training dataset, both in time and memory. While many approximations exist, all incur inevitable approximation error. Recent work accounts for this error in the form of computational uncertainty, which enables -- at the cost of quadratic complexity -- an explicit tradeoff between computational efficiency and precision. Here we extend this development to model selection, which requires significant enhancements to the existing approach, including linear-time scaling in the size of the dataset. We propose a novel training loss for hyperparameter optimization and demonstrate empirically that the resulting method can outperform SGPR, CGGP and SVGP, state-of-the-art methods for GP model selection, on medium to large-scale datasets. Our experiments show that model selection for computation-aware GPs trained on 1.8 million data points can be done within a few hours on a single GPU. As a result of this work, Gaussian processes can be trained on large-scale datasets without significantly compromising their ability to quantify uncertainty -- a fundamental prerequisite for optimal decision-making.

Bio: Jonathan Wenger is a postdoctoral research scientist at Columbia University's Department of Statistics and Zuckerman Institute working with Prof. John Cunningham. He earned a PhD in Computer Science from the University of Tübingen under the supervision of Prof. Philipp Hennig. Jonathan’s research focuses on resource-efficient methods for large-scale probabilistic machine learning. Much of his work contributes to the field of probabilistic numerics, which views numerical algorithms through the lens of probabilistic inference. This perspective enables the acceleration of learning algorithms via an explicit trade-off between computational efficiency and predictive precision.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: Empirical likelihood is a popular non-parametric method for inference. The resulting profile empirical likelihood function has many similar properties to its parametric counterpart. The empirical likelihood confidence intervals achieve higher coverage precision compared to its parametric counterpart but tend to have below nominal-level coverage probability. To address this issue, researchers have proposed adjusted empirical likelihood and Bartlett corrected empirical likelihood methods to achieve high-order coverage precision. Still, when the sample size is small, the coverage remains unsatisfactory. In my thesis, we develop a computer experiment data-driven approach to improve the coverage precisions of empirical likelihood confidence regions.

The maximum empirical likelihood estimator, just like its parametric counterpart, shares many nice properties. However, the optimal properties cannot be utilized unless we know the local maximum at hand is close to the unknown true parameter value. To overcome this obstacle, we first propose a set of conditions under which the global maximum is consistent. We then develop a global maximum test to ascertain if the local maximum at hand is, in fact, the global maximum. Furthermore, we invent a global maximum remedy to ensure global consistency by expanding the set of estimating functions under empirical likelihood.

For non-regular models such as finite normal mixture models, the MLE is not well-defined because of the unboundedness of likelihood. To address this issue, researchers have proposed penalized likelihood and constrained MLE to consistently estimate the mixing distribution. However, the consistency of these method is established under the assumption that the component covariance matrices of the true mixing distribution are non-singular. We relax this restriction to show that the penalized MLE is still consistent when component covariance matrices of the true mixing distribution are singular. We also invent a test for degeneracy of finite normal mixture model.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: The study explores the identification of strongly lensed galaxies, rare astronomical phenomena where massive objects bend light from distant sources, creating magnified and distorted images. Strongly lensed galaxies are crucial in astronomy as they provide insights into dark matter distribution, galaxy mass profiles, and cosmological parameters. To efficiently identify these lenses from vast datasets, images were ranked based on their probability of being strong lens candidates. A Learning-to-Rank (LTR) approach using Support Vector Machines (SVM) was implemented and compared with Convolutional Neural Networks (CNNs) and other classifiers. LTR with SVM demonstrated superior performance, achieving a high AUC and accuracy, outperforming CNNs in both efficiency and classification precision. This method facilitates efficient candidate selection, enhancing the potential for cosmological studies.

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: We develop the model-based latent causal socioeconomic health (LaCSH) index, with uncertainty bounds, at the national level. Extending the latent health factor index (LHFI) modeling approach to assess ecosystem health, LaCSH integratively models the hierarchical relationship among the nation’s societal health or well-being (latent / intangible), socio-economic metrics (e.g., GDP), the covariates that drive the notion of well-being (e.g., natural resources), and a continuous variable that reflects policy (e.g., government mandated maternity leave days). In addition to making statistical inference for socio-economic health, LaCSH facilitates the evaluation of potential causal impact of the policy on health. A formal spatial component in the LaCSH framework allows us to compare the socio-economic health of countries around the world based on various metrics, covariates, and two different policy variables that pertain to socio-economic well-being. This is joint work led by FS Kuh with AHWestveld (https://arxiv.org/abs/2009.12217)

To join this seminar virtually: Please request Zoom connection details from ea@stat.ubc.ca.

Abstract: Our Sun is dynamic with solar activity peaking approximately every 11 years. This rise in activity increases the chance of rare solar wind events (e.g. coronal mass ejections). The most recognizable effect of this rise in solar activity is the increase of planetary aurorae. We are currently approaching the peak of solar cycle 25 and in the last few months have observed several large coronal mass ejections arrive at Earth, spawning visible low-latitude aurora (including over Vancouver).

Spacecraft assets throughout the solar system observe our Sun and the solar wind. However, these datasets can only provide discontinuous spatiotemporal observations of a very large and dynamic system. Traditionally these observational assets are combined with high-fidelity physical models (e.g. magnetohydrodynamics). But these models are computationally expensive which limits the potential number of simulations. This bottleneck (sparse datasets, expensive forward physics-based models) is a ubiquitous challenge for inverse problems in the Earth and planetary sciences. In the case of Mars, this methodological bottleneck has limited our understanding of how the rise and fall of solar cycle activity affects planetary habitability.

In this presentation, I will pose estimating the solar wind during a recent rare solar wind event at Mars as an inverse problem. I will then discuss a Bayesian approach to this inverse problem using Gaussian processes as a low-fidelity emulator of a physics-based model and the scientific conclusions we are gaining about Mars from this effort. I will conclude with an outlook for simulation-based inference in Earth and planetary sciences.

Bio: Dr. Abigail (Abby) Azari is a Data Science Post-Doctoral Fellow in the Department of Earth, Ocean and Atmospheric Sciences where she works with Dr. Catherine Johnson (EOAS), Dr. Lindsey Heagy (EOAS), and Dr. Frank Wood (CS). Dr. Azari is a member of the NASA MAVEN Science Team; a spacecraft that has orbited Mars since 2014. Her research generally focuses on machine learning for scientific insights about planetary space environments. She was previously a postdoc at the UC Berkeley’s Space Sciences Lab. She received her Ph.D. in 2020 from the University of Michigan where she was an NSF Graduate Research Fellow and a NASA Earth and Space Sciences Fellow.

In January 2025, Dr. Azari will be joining the University of Alberta’s Physics and Electrical and Computer Engineering departments as an incoming faculty member and fellow of the Alberta Machine Intelligence Institute.