All talks are in Pacific Time. Subject to change. Please note there are no abstracts for this workshop.

–
Coffee and Check-In
–
Opening Remarks
–
Multicalibration and Outcome Indistinguishability I
Michael Kim (UC Berkeley )
–
Coffee Break
–
Multicalibration and Outcome Indistinguishability II
Michael Kim (UC Berkeley )
–
Lunch Break
–
Multigroup Fairness and Loss Minimization
Parikshit Gopalan (Apple)
–
Coffee Break
–
Validity of Decision Making Algorithms
Amanda Coston (CMU)
–
Reception
–
Coffee and Check-In
–
Calibration: Unbiased Answers to Arbitrary Questions
Dean Foster (Amazon)
–
Coffee Break
–
Robust Multivalid Conformal Prediction
Christopher Jung (Stanford)
–
Online Omniprediction
Sumegha Garg (Stanford)
–
Lunch Break
–
Measuring Distribution Drift via Multicalibration
Udi Wieder (VMware)
–
Loss Minimization Yields Multicalibration for Large Neural Networks
Adam Kalai (Microsoft)
–
Coffee Break
–
Algorithms for Multigroup Learning
Daniel Hsu (Columbia)
–
A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning
Nika Haghtalab (UC Berkeley)
–
Evening Session at 2nd Floor Collaboration Area: Introductions and Informal Discussions
–
Coffee and Check-In
–
Unfairness Across the Machine Learning Pipeline
Emily Black (Stanford)
–
Coffee Break
–
Difficult Lessons on Social Prediction from Wisconsin Public Schools
Juan Carlos Perdomo (UC Berkeley)
–
Is Your Model Predicting the Past?
Moritz Hardt (UC Berkeley)
–
Lunch Break
–
Robust Conditional Average Treatment Effect Estimation via Multi-Accurate Learning
Christoph Kern (LMU Munich)
–
What Statistics Can We Multicalibrate? A Characterization via Property Elicitation
Georgy Noarov (University of Pennsylvania)
–
Coffee Break
–
Rump Session
–
Coffee and Check-In
–
From Pseudorandomness to Multigroup Fairness and Back
Rachel (Huijia) Lin (University of Washington)
–
Coffee Break
–
Complexity-theoretic Implications of Multicalibration: Hardcore Sets, Dense Models, and Pseudoentropy
Silvia Casacuberta Puig (Harvard)
–
Indistinguishable Generative Models of Huge Objects
Inbal Livni (Stanford)
–
Lunch Break
–
Interactive Proofs for Verifiable Data Science (in-person only, no livestream)
Guy Rothblum (Apple)
–
Coffee Break
–
Sample Complexity Bounds for Realizable Multicalibration
Charlotte Peale (Stanford)
–
Algorithmic Collective Action in Machine Learning
Tijana Zrnic (UC Berkeley)
–
Coffee and Check-In
–
Who is Fairer: Humans vs. Machines?
Frauke Kreuter (University of Maryland)
–
Coffee Break
–
Omnipredictors for Constrained Optimization
Lunjia Hu (Stanford)
–
Measuring Our Chances: Risk Prediction in this World and its Betters
Cynthia Dwork (Harvard)
–
Lunch Break
–
Social Norm Bias: Residual Harms of Fairness-Aware Algorithms
Maria De-Arteaga (University of Texas)
–
On the Causal Foundations of Fair Machine Learning
Drago Plečko (Columbia University)
–
Connections Between Multicalibration and Doubly Robust Estimation
David Bruns-Smith (UC Berkeley)