All talks are listed in Pacific Time.

–
Coffee & Check In
–
Opening Remarks
–
Tractable Probabilistic Circuits
Guy Van den Broeck (UCLA)
–
Break
–
Neural Networks And Spurious Correlations
Aditi Raghunathan (UC Berkeley)
–
Learning Restricted Boltzman Machines
Ankur Moitra (MIT)
–
Lunch
–
Learning Ill-Conditioned Gaussian Graphical Models
Raghu Meka (UCLA)
–
Preconditioning In Sparse Linear Regression Using Graphical Structure
Frederic Koehler (Stanford)
–
Break
–
Causal Matrix Completion
Anish Agarwal (UC Berkeley)
–
Parameter Estimation For Undirected Graphical Models With Hard Constraints
Kavita Ramanan (Brown University)
–
Reception
–
Coffee & Check In
–
Efficient Distance Estimation And Causal Inference For Discrete Models
Arnab Bhattacharyya (National University of Singapore)
–
Break
–
Identifying Mixture Models
Leonard J. Schulman (Caltech)
–
Identifying Mixtures Of Bayesian Network Distributions
Yuval Rabani (The Hebrew University of Jerusalem)
–
Lunch
–
Asymptotically Best Causal Effect Identification With Multi-Armed Bandits
Silvia Chiappa (DeepMind)
–
Confounding-Robust Policy Evaluation In Infinite-Horizon Reinforcement Learning
Angela Zhou (Berkeley)
–
Break
–
Stability Of Causal Identification From The Perspective Of Condition Numbers
Piyush Srivastava (Tata Institute of Fundamental Research)
–
Causalsim: Trace-Driven Simulation For Network Protocols
Devavrat Shah (MIT)
–
Open Problem Session (In-Person Only)
–
Coffee & Check In
–
A Multi-Group Approach To Algorithmic Fairness
Guy Rothblum (Weizmann Institute of Science)
–
Break
–
Decision-Making Under Miscalibration
Gal Yona (Weizmann Institute)
–
Multicalibration, Universal Adaptability and Causality
Omer Reingold (Stanford University)
–
Lunch
–
Algorithmic Fairness From The Lens Of Causality And Information Theory
Sanghamitra Dutta (JP Morgan AI Research)
–
Orthogonal Statistical Learning
Vasilis Syrgkanis (Microsoft Research)
–
Theoretically Speaking — Opportunities for the Application of Quantitative Models in a Fully Integrated Healthcare System
Noa Dagan (Harvard, Clalit Research Institute and Ben-Gurion University), Noam Barda  (Harvard, Tel-HaShomer Medical Center and Ben-Gurion University)
–
Coffee & Check In
–
The Approximate Implication Problem For Probabilistic Graphical Models
Batya Kenig (Technion, Israel Institute of Technology)
–
Break
–
Challenges For Causal Inference On Digital Platforms
Moritz Hardt (Max Planck Institute for Intelligent Systems)
–
Active Invariant Causal Prediction: Experiment Selection Through Stability
Christina Heinze-Deml (Apple Health AI)
–
Lunch
–
Graph Agnostic Randomized Experimental Design under Heterogeneous Linear Network Interference
Christina Yu (Cornell University)
–
Collaborative Causal Discovery With Atomic Interventions
Shiva Kasiviswanathan (Amazon)
–
Break
–
New Approaches To Learning Nonparametric (Latent) CausalGraphical Models
Bryon Aragam (University of Chicago)
–
Kernel Methods For Causal Inference
Rahul Singh (MIT)