2026
Student Seminar: Zixuan Qin
1:00–1:30 pm Jones 111
Wednesday, February 18, 2026, at 1:00 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis Presentation
Zixuan Qin Department of Statistics, The University of Chicago
“Operator Learning and Bispectrum-Guided Diffusion for Functional Multi-Reference Alignment”
Joint Statistics and DSI Colloquium: Ana-Andreea Stoica
2:00–3:00 pm DSI 105
Ana-Andreea Stoica
Research Group Leader in the Social Foundations of Computation Department
Max Planck Institute for Intelligent Systems
Title: Designing for Society: AI in Networks, Markets, and Platforms
Abstract: AI systems increasingly mediate how people access information, economic opportunities, and essential services. Yet when deployed in social environments—online platforms, labor markets, and information ecosystems—AI interacts with complex human behavior, strategic incentives, and structural inequality. This talk focuses on foundational challenges and opportunities for AI systems: how to design and evaluate algorithmic interventions in complex social environments. I will present recent work on causal inference under competing treatments, which formalizes how competition for user attention and strategic behavior among experimenters distort experimental data and invalidate naïve estimates of algorithmic impact. By modeling experimentation as a strategic data acquisition problem, we show how evaluation itself becomes an optimization problem, and we derive mechanisms that recover meaningful estimates despite interference and competition. I connect this problem to deriving foundational properties of AI systems that enable responsible and efficient algorithmic design. Beyond this case study, the talk highlights broader implications for the design and evaluation of AI systems in networks, markets, and platforms. I argue that responsible deployment requires rethinking evaluation methodologies to account for incentives, feedback loops, and system-level effects, and I outline how algorithmic and statistical tools can support more accountable and socially aligned AI systems.
Student Seminar: Jose Cruzado
2:00–2:30 pm Jones 111
Monday, February 16, 2026, at 2:00 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis Presentation
Jose Cruzado, Department of Statistics, The University of Chicago
“Expected Gradient Outer Product Reparameterization in Deep ConvolutionalNetworks”
Student Seminar: Kaushik Kancharla
9:00–9:30 am Jones 111
Wednesday, February 11, 2026, at 9:00 AM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis Presentation
Kaushik Kancharla, Department of Statistics, The University of Chicago
“The Intraday Dynamics of the Volatility Term Structure”
Student Seminar: Hunter Chen
1:00–1:30 pm Kent 106
Tuesday, February 10, 2026, at 1:00 PM, in Kent 106, 1427 East 60th Street
Master’s Thesis Presentation
Hunter Chen, Department of Statistics, The University of Chicago
“Empirical Bayes learning from selectively reported confidence intervals”
Department of Computer Science and Data Science Institute Presents: Weijia Shi
2:30–3:30 pm DSI 105
Weijia Shi
PhD Candidate
University of Washington
Title: Breaking the Language Model Monolith
Abstract: Language models (LMs) are typically monolithic: a single model storing all knowledge and serving every use case. This design presents significant challenges; they often generate factually incorrect statements, require costly retraining to add or remove information, and face serious privacy and copyright issues. In this talk, I will discuss how to break this monolith by introducing modular architectures and training algorithms that separate capabilities across composable components. I’ll cover two forms of modularity: (1) External modularity, which augments LMs with external tools like retrievers to improve factuality and reasoning; and (2) internal modularity, which builds inherently modular LMs from decentrally trained components to enable flexible composition and an unprecedented level of control.
Student Seminar: Haewon Hwang
1:00–1:30 pm Jones 226
Monday, February 9, 2026, at 1:00 PM, in Jones 226, 5747 S. Ellis Avenue
Master’s Thesis Presentation
Haewon Hwang, Department of Statistics, The University of Chicago
“Media Violence and Criminal Behavior: evidence from local movie demand”
Student Seminar: Yunsheng Lu
4:00–4:30 pm Jones 111
Friday, February 6, 2026, at 4:00 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis Presentation
Yunsheng Lu Department of Statistics, The University of Chicago
“Causal Alignment of Reward Models via Response-to-Prompt Prediction”
Joint Statistics and DSI Colloquium: Jingfeng Wu
4:00–5:00 pm DSI 105
Jingfeng Wu
Postdoctoral Fellow
University of California, Berkeley
Title:
Towards a Less Conservative Theory of Machine Learning: Unstable Optimization and Implicit Regularization
Abstract:
Deep learning’s empirical success challenges the “conservative” nature of classical optimization and statistical learning theories. Classical theory mandates small stepsizes for training stability and explicit regularization for complexity control. Yet, deep learning leverages mechanisms that thrive beyond these traditional boundaries. In this talk, I present a research program dedicated to building a less conservative theoretical foundation by demystifying two such mechanisms:
1. Unstable Optimization: I show that large stepsizes, despite causing local oscillations, accelerate the global convergence of gradient descent (GD) in overparameterized logistic regression.
2. Implicit Regularization: I show that the implicit regularization of early-stopped GD statistically dominates explicit $\ell_2$-regularization across all linear regression problem instances.
I further showcase how the theoretical principles lead to practice-relevant algorithmic designs (such as Seesaw for reducing serial steps in large language model pretraining). I conclude by outlining a path towards a rigorous understanding of modern learning paradigms.
Statistics Colloquium: Sungwoo Jeong
11:30 am–12:30 pm Jones 303
Sungwoo Jeong
Department of Mathematics
Cornell University
Title: “Convergence of Two Kernel Algorithms: Continuous Analogues of the SVD and the Cholesky Decomposition”
Abstract: Kernels have been shown to be effective in numerous applications. We discuss some misconceptions and facts about why kernels are powerful in practice. To investigate this, we consider two expansions that encode fundamental kernel structures: the kernel analogue of the SVD and the Cholesky decomposition.
First, the convergence of the kernel SVD (SVE) is equivalent to the existence of a corresponding functional space such as the reproducing kernel Hilbert space (RKHS). For general kernels, such as self-attention in neural networks, it is still unclear whether the SVE converges. We prove a surprising result showing that kernel continuity alone is not enough to guarantee this convergence. At the same time, we provide a new sufficient condition for convergence that helps explain why kernels work well in practice.
The kernel Cholesky algorithm is another fundamental tool used in applications such as Gaussian process regression (Bayesian inference on functions). While it is empirically observed that the Cholesky algorithm converges for smooth kernels, no rigorous result exists for kernels with weaker regularity than $C^2$. We prove a new convergence result for Lipschitz continuous kernels, together with an explicit convergence rate that sharply agrees with what is observed in practice.