-
Tractable Agreement Protocols
On May 2, 2025 at 11:00 am till 12:00 pm E18-304Aaron Roth, University of Pennsylvania
-
How should we do linear regression?
On April 25, 2025 at 11:00 am till 12:00 pm E18-304Richard Samworth, University of Cambridge
-
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…
