2025
Bahadur Memorial Lectures: John Lafferty (Day 1)
11:30 am–12:30 pm Jones 303
Title: Abstraction in Artificial and Natural Intelligence: Part I: Relational and Sequential Reasoning
Abstract: Two broad types of natural intelligence are used by humans (and other animals). One type is used to acquire semantic and procedural knowledge about the world. Another type is used to identify novel associations and relations. This second type of intelligence often requires very little data, but significant time to “think” and search for solutions; recent AI models mimic this type of intelligence using “chain of thought.” We present a framework for modeling relational learning and abstraction, using an inductive bias called the relational bottleneck. To assess the flexibility of the relational bottleneck, a universal approximation theory is developed. To analyze the advantages of sequential reasoning, an extension of statistical learning theory for autoregressive models is proposed. This offers insight into how chain of thought sequential supervision can improve learning efficiency.
Student Seminar: Yilong Chen
1:00–1:30 pm Jones 111
Monday April 28, 2025, at 1:00 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis l Presentation
Yilong Chen, Department of Statistics, The University of Chicago
“Categorical Variational Autoencoder for Count Tensor Decomposition”
Student Seminar: Xiang Lu
2:00–2:30 pm Jones 111
Monday April 28, 2025, at 2:00 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis l Presentation
Xiang Lu, Department of Statistics, The University of Chicago
“Special orthogonal, special unitary, and symplectic groups as products of Grassmannians”
Student Seminar: Hongyi Zhang
2:30–3:00 pm Jones 111
Monday April 28, 2025, at 2:30 PM, in Jones 111, 5747 S. Ellis Avenue
Master’s Thesis l Presentation
Hongyi Zhang, Department of Statistics, The University of Chicago
“Robust Point-Set Registration via Non-Convex Optimization under Noise”