-
Same Root Different Leaves: Time Series and Cross-Sectional Methods in Panel Data
On April 18, 2025 at 11:00 am till 12:00 pm E18-304Dennis Shen, University of Southern California
-
Causal Inference on Outcomes Learned from Text
On April 11, 2025 at 11:00 am till 12:00 pm E18-304Jann Spiess, Stanford University
-
The value of information in model assisted decision-making
On April 4, 2025 at 11:00 am till 12:00 pm E18-304Jessica Hullman, Northwestern University
-
Structured Topic Modeling: Leveraging Sparsity and Graphs for Improved Inference
On March 21, 2025 at 11:00 am till 12:00 pm E18-304Claire Donnat, University of Chicago
-
Feature Learning and Scaling Laws in Two-layer Neural Networks: A high dimensional analysis
On March 14, 2025 at 11:00 am till 12:00 pm E18-304Murat A. Erdogdu, University of Toronto
-
Finite-Particle Convergence Rates for Stein Variational Gradient Descent
On March 7, 2025 at 11:00 am till 12:00 pm E18-304Krishna Balasubramanian, University of California – Davis
-
Two Approaches Towards Adaptive Optimization
On February 28, 2025 at 11:00 am till 12:00 pm E18-304Ashia Wilson, MIT
-
Towards a ‘Chemistry of AI’: Unveiling the Structure of Training Data for more Scalable and Robust Machine Learning
On February 21, 2025 at 11:00 am till 12:00 pm E18-304Abstract: Recent advances in AI have underscored that data, rather than model size, is now the primary bottleneck in large-scale machine learning performance. Yet, despite this shift, systematic methods for dataset curation, augmentation, and optimization remain underdeveloped. In this talk, I will argue for the need for a Chemistry of AI–a paradigm that, like the…
-
Inference for ATE & GLM’s when p/n→δ∈(0,∞)
On February 7, 2025 at 11:00 am till 12:00 pm E18-304Abstract In this talk we will discuss statistical inference of average treatment effect in measured confounder settings as well as parallel questions of inferring linear and quadratic functionals in generalized linear models under high dimensional proportional asymptotic settings i.e. when p/n→δ∈(0,∞) where p, n denote the dimension of the covariates and the sample size respectively…
-
Deep Learning Methods for Public Health Prediction
On December 10, 2024 at 2:00 pm till 3:00 pm E18-304Alexander Rodríguez, University of Michigan
