2025
Statistics Colloquium: Chiara Sabatti
11:30 am–12:30 pm Jones 303
Chiara Sabatti, Department of Biomedical Data Science and Statistics, Stanford University
Title: “Searching for local associations while controlling the false discovery rate”
Abstract: In this talk I will describe local conditional hypotheses that express how the relation between explanatory variables and outcomes changes across different contexts, described by covariates. I will then introduce efficient testing strategies for these hypotheses.
The motivation for this work comes from genetics and genomics. For example, as the evidence obtained from genome-wide association studies accumulates, it has become apparent that some genetic variants carry information on phenotypes in some populations and not in others. There are multiple explanations contributing to this phenomenon. Among others, it is possible that some genetic variations might be relevant for the trait of interest only in specific environmental conditions, the exposure to which varies across human populations.
To identify the combination of explanatory variables and covariates that influence an outcome, we build upon the knockoff framework for FDR control and powerful pre-screening strategies. Specifically, the method we propose can leverage any model for the identification of data-driven hypotheses pertaining to different contexts. Then it rigorously tests these hypotheses without succumbing to selection bias. The approach is efficient and does not require sample splitting. We demonstrate the effectiveness of our method through numerical experiments and by studying the genetic architecture of waist/hip ratio across different sexes in the UK Biobank.
This work is in collaboration with Matteo Sesia and Paula Gablenz.
Student Seminar: Yeo Jin Jung
10:00 am–12:00 pm Jones 111
Tuesday, October 28, 2025, at 10:00 AM, in Jones 111, 5747 S. Ellis Avenue
Dissertation Proposal Presentation
Yeo Jin Jung, Department of Statistics, The University of Chicago
“Structured Representation Learning in High-dimensional Data”
Student Seminar: Yiheng Yang
3:30–4:00 pm Jones 111
Monday, October 27, 2025, at 3:30 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis l Presentation
Yiheng Yang, Department of Statistics, The University of Chicago
“Sensitivity Analysis for Permutations of Hidden Biases in Matched Observational Studies”
Statistics Colloquium: Armeen Taeb
11:30 am–12:30 pm Jones 303
Armeen Taeb, Department of Statistics, University of Washington
Title: Complex Model Selection via Posets: Correlated Regression, Causal Graphs, and Phylogenetic Trees
Abstract: In this talk, we consider model selection in complex model spaces, focusing on three case studies: regression with correlated features, causal graphs, and consensus phylogenetic trees. Standard selection criteria often fail to account for the structural and equivalence constraints inherent to such problems. To address this, we represent model spaces as partially ordered sets, which provide principled notions of similarity between models, allowing for more meaningful measures of model quality. In correlated regression, this framework yields refined notions of false positive error and feature stability. In causal discovery, it offers a unified, model-oriented way to define distances between graphs. Finally, in phylogenetics, it provides a procedure that yields a stable tree from a set of candidate trees, and enables quantification and control of false positive error.
Bio: Armeen is an assistant professor in the Department of Statistics at the University of Washington. Before UW, he was a postdoc at ETH Zurich and received his PhD at Caltech. His research interests lie at the interface of optimization and statistics. His work currently focuses on model selection in non-traditional settings and learning provably optimal causal models from data.
Student Seminars: Soumyabrata Kundu
9:30–11:30 am Jones 111
Monday, October 27, 2025, at 9:30 AM, in Jones 111, 5747 S. Ellis Avenue
Dissertation Defense Presentation
Soumyabrata Kundu, Department of Statistics, The University of Chicago
“Steerable Architectures for Computer Vision”
Student Seminar: Angela Wang
10:30–11:00 am Jones 111
Tuesday, October 21, 2025, at 10:30 AM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis l Presentation
Angela Wang, Department of Statistics, The University of Chicago
“TBA”
Statistics Colloquium: Zhou Fan
11:30 am–12:30 pm Jones 303
Zhou Fan, Department of Statistics and Data Science, Yale University
Title: “Empirical Bayes Langevin dynamics in the linear model”
Abstract: In many applications of statistical estimation via sampling, one may wish to sample from a highdimensional target distribution that is adaptively evolving to the samples already seen. I will present an example of such dynamics in a Bayesian linear model, given by a Langevin diffusion for sampling from a posterior distribution that adapts to implement empirical Bayes learning of the prior. In this talk, I hope to discuss a positive result on nonparametric consistency for this empirical Bayes learning task, a motivation of these dynamics from a perspective of Wasserstein gradient flows, and a precise characterization of the dynamics in a mean-field setting of i.i.d. regression design.
Based on joint work with Yandi Shen, Leying Guan, Justin Ko, Bruno Loureiro, Yue M. Lu, and Yihong Wu.
Statistics Colloquium: Peter Hoff
11:30 am–12:30 pm Jones 303
Peter Hoff, Department of Statistical Science, Duke University
Title: “Core Shrinkage Covariance Estimation for Matrix-variate Data”
Abstract: A separable covariance model for a random matrix provides a parsimonious description of the covariances among the rows and among the columns of the matrix, and permits likelihood-based inference with a very small sample size. However, in many applications the assumption of exact separability is unlikely to be met, and data analysis with a separable model may overlook or misrepresent important dependence patterns in the data. In this article, we propose a compromise between separable and unstructured covariance estimation. We show how the set of covariance matrices may be uniquely parametrized in terms of the set of separable covariance matrices and a complementary set of “core” covariance matrices, where the core of a separable covariance matrix is the identity matrix. This parametrization defines a Kronecker-core decomposition of a covariance matrix. By shrinking the core of the sample covariance matrix with an empirical Bayes procedure, we obtain an estimator that can adapt to the degree of separability of the population covariance matrix.
2025 Takintayo Akinbiyi Memorial Award Ceremony
11:15–11:30 am Jones 303
Please join us in Jones 303 as we present the second annual Takintayo Akinbiyi Memorial Award for Academic Excellence in Statistics.
Statistics Colloquium: Cong Ma
11:30 am–12:30 pm Jones 303
Cong Ma, Department of Statistics and the College, University of Chicago
Title: Learning with Few Updates: Batched Contextual Bandits
Abstract: Sequential decision-making is central to modern statistics, with applications ranging from clinical trials to online recommendation systems. Classical theory assumes that policies can be updated at every step, but in many modern experiments decisions can only be revised at a few discrete times, leading to batching constraints. Such limits on adaptivity inevitably affect statistical performance, raising a central question: how much efficiency is lost, and how many updates are needed for optimal learning?
I will address this question in the setting of contextual bandits with smooth reward functions. I will first present a success story: when the margin parameter is known, only $\log\log T$ batches are needed to match the minimax regret rates of the fully online setting—showing that very limited adaptivity is enough for optimal learning. I will then turn to the more subtle case where the margin parameter is unknown. In the online regime, adaptation comes at no cost, but batching introduces a genuine barrier: there is a provable statistical price to be paid. I will describe recent results that sharply characterize this price under fixed batch grids and highlight the open question of whether adaptive batch schedules can close the gap.