–
Coffee and Check-In
–
Opening Remarks
–
A Discrepancy-Based Theory of Adaptation
Mehryar Mohri (Google Research & NYU)
–
Label Noise: Ignorance is Bliss
Clayton Scott (University of Michigan)
–
Break
–
Does Distribution Shift Matter In the Era of Pre-trained Language Models?
Robin Jia (University of Southern California)
–
The Data Addition Dilemma
Irene Y Chen (UC Berkeley)
–
Lunch (on your own)
–
How Transformers Learn Causal Structure with Gradient Descent
Jason Lee (Princeton University)
–
Pseudo-Labeling for Covariate Shift Adaptation
Kaizheng Wang (Columbia University)
–
Poster Session and Reception
–
Coffee and Check-In
–
TBD
Nika Haghtalab (UC Berkeley)
–
Transfer learning for weak-to-strong generalization
Yuekai Sun (University of Michigan)
–
Break
–
Distribution shift in ecological data: generalization vs. specialization,
Sara Beery (MIT)
–
Transfer learning via local convergence rates of the nonparametric least squares estimator
Johannes Schmidt-Hieber (University of Twente)
–
Lunch (on your own) and Lunchtime Activity
–
The Modulus of Transfer
Steve Hanneke (Purdue University)
–
User-level and federated local differential privacy
Yi Yu (University of Warwick)
–
Optional Sunset Hike
–
Coffee and Check-In
–
On Spurious Associations and LLM Alignment
Victor Veitch (University of Chicago)
–
TBD
Zachary Lipton (Carnegie Mellon University)
–
Break
–
Causally motivated robustness to shortcut learning
Maggie Makar (University of Michigan)
–
Lunch (on your own) and Table Discussions (click for sign up sheet)
Sign up for a group discussion here (click here)
–
TBD
Emma Brunskill (Stanford University)
–
Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains or the Whole Domain
Tengyu Ma (Stanford University)
–
Break
–
Language-guided Adaptation
Trevor Darrrell (UC Berkeley)
–
Coffee and Check-In
–
Distributional Shifts and Spectral Risks
Zaid Harchaoui (University of Washington)
–
Adaptive Data Collection via Autoregressive Generation
Hongseok Namkoong (Columbia University)
–
Break
–
Scalably Understanding AI with AI
Jacob Steinhardt (UC Berkeley)
–
TBD
Kamalika Chaudhuri (UC San Diego)
–
Lunch (on your own)
–
Open-Source and Science in the Era of Foundation Models
Percy Liang (Stanford University)
–
Domain Adaptation-- 20 years of theory chasing practice
Shai Ben-David (University of Waterloo)
–
Break
–
Panel Discussion
Rich Zemel (Columbia University), Shai Ben-David (University of Waterloo and Vector Institute ), Kamalika Chaudhuri (UC San Diego), Percy Liang, Hongseok Namkoong (Columbia University)