All talks listed in Pacific Time. Schedule subject to change.

–
Coffee and Check In
–
Opening Remarks
–
Learning from Dynamics
Ankur Moitra (Massachusetts Institute of Technology)
–
Testing Noise Assumptions of Learning Algorithms
Arsen Vasilyan (Simons Institute)
–
Break
–
The Truth About Your Lying Calibrated Forecaster: How to Design Truthful Calibration Measures
Nika Haghtalab (UC Berkeley)
–
Talk by
Ali Kavis (UT Austin)
–
Lunch (on your own)
–
Data curation for LLM Pre-training and Post-Training: Creating massive datasets for the AI open-source community with the Datacomp project.
Alex Dimakis (UT Austin)
–
Bypassing the Impossibility of Online Learning Thresholds: Unbounded Losses and Transductive Priors
Nikita Zhivotovskiy (UC Berkeley)
–
Coffee and Check In
–
Revisiting Scalarization in Multi-Task Learning
Han Zhao (University of Illinois Urbana-Champaign)
–
Understanding Contrastive Learning and Self-training
Sujay Sanghavi (UT Austin and Amazon)
–
Break
–
Omnipredicting Single-Index Models with Multi-Index Models
Kevin Tian (UT Austin)
–
Talk by
Tselil Schramm (Stanford University)
–
Poster Session and Appetizers
–
Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)
Sean Welleck (Carnegie Mellon University)
–
RMK Lecture Reception (Light Refreshments)
–
The Science of Modern Machine Learning: New Opportunities for Theory | Richard M. Karp Distinguished Lecture
Peter Bartlett (Simons Institute, UC Berkeley)
–
Coffee and Check In
–
Robust Mixture Learning when Outliers Overwhelm Small Groups
Fanny Yang (ETH Zurich)
–
Learning General Gaussian Mixtures With Efficient Score Matching
Vasilis Kontonis (UT Austin)
–
Break
–
Talk by
Mahdi Soltanolkotabi (University of Southern California)
–
Talk by
Zaid Harchaoui (University of Washington)