All talks will be held in Pacific Time.

*Schedule subject to change*

–
Light Breakfast and Check-In
–
Light Breakfast and Check-In
–
Opening Remarks
–
KEYNOTE: A (Con)Sequential View of Information for Statistical Learning and Optimization
Tara Javidi (UC San Diego)
–
KEYNOTE: A (Con)Sequential View of Information for Statistical Learning and Optimization
Tara Javidi (UC San Diego)
–
Coffee Break
–
Coffee Break
–
Majorizing Measures, Codes, and Information
Maxim Raginsky (University of Illinois, Urbana-Champaign)
–
Majorizing Measures, Codes, and Information
Maxim Raginsky (University of Illinois, Urbana-Champaign)
–
On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
Cynthia Rush (Columbia)
–
On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations
Cynthia Rush (Columbia)
–
Secure Distributed Matrix Multiplication
Rafael D'Oliveira (Clemson University)
–
Secure Distributed Matrix Multiplication
Rafael D'Oliveira (Clemson University)
–
Lunch
–
Lunch
–
Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values
Haewon Jeong (UC Santa Barbara)
–
Optimal Neural Network Compressors and the Manifold Hypothesis
Aaron Wagner (Cornell University)
–
Coffee Break
–
Coffee Break
–
Reception
–
Generalization bounds for Neural Network Based Decoders
Ravi Tandon (University of Arizona)
–
Generalization bounds for Neural Network Based Decoders
Ravi Tandon (University of Arizona)
–
Information-theoretic Foundations of Generative Adversarial Models: Addressing Training Instabilities
Lalitha Sankar (Arizona State University)
–
A loss function perspective for robust machine learning
Lalitha Sankar (Arizona State University)
–
Reception
–
Light Breakfast and Check-In
–
KEYNOTE: Differential Privacy & Variants
Ilya Mironov (Google)
–
KEYNOTE: Differential Privacy & Variants
Ilya Mironov (Meta)
–
Coffee Break
–
Coffee Break
–
Contraction of Markov kernels and differential privacy (PART II)
Shahab Asoodeh (McMaster University)
–
Contraction of Markov kernels and differential privacy (PART II)
Shahab Asoodeh (Ravi)
–
Contraction of Markov Kernels and Differential Privacy (PART I)
Mario Diaz (Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas…
–
Contraction of Markov Kernels and Differential Privacy (PART I)
Mario Diaz (Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas…
–
The Saddle-Point Accountant for Differential Privacy
Oliver Kosut (Arizona State University)
–
The Saddle-Point Accountant for Differential Privacy
Oliver Kosut (Arizona State University)
–
Lunch
–
Lunch
–
Fundamental trade-offs in FL/FA + sparsity + DP + communication constaints
Peter Kairouz (Google)
–
Towards “One-Shot” Privacy Auditing and Estimation
Peter Kairouz (Google)
–
Improving Accuracy-Privacy Tradeoff via Model Reprogramming
Pin-Yu Chen (IBM Research)
–
Improving Accuracy-Privacy Tradeoff via Model Reprogramming
Pin-Yu Chen (IBM Research)
–
Coffee Break
–
Coffee Break
–
Poster Session (Click to view Presenters & Topics)
–
Poster Session
–
Light Breakfast and Check-In
–
KEYNOTE: Variational Formulations and Distributed Convex Optimization Methods for Generative Modeling in High Dimensions
Todd Coleman (UC San Diego)
–
KEYNOTE: Variational Formulations and Distributed Convex Optimization Methods for Generative Modeling in High Dimensions
Todd Coleman (UC San Diego)
–
Coffee Break
–
Coffee Break
–
Fair, Explainable, and Lawful Machine Learning for High-Stakes Applications
Sanghamitra Dutta (University of Maryland, College Park)
–
Topic: Fairness, Explainability, Information Theory (Exact Title: TBD)
Sanghamitra Dutta (University of Maryland, College Park)
–
Information Thresholds in Structure Estimation
Anand Sarwate (Rutgers University)
–
Optimal Neural Network Compressors and the Manifold Hypothesis
Aaron Wagner (Cornell University)
–
Decision making with information-theoretic constraints
Matthieu Bloch (Georgia Institute of Technology)
–
Decision making with information-theoretic constraints
Matthieu Bloch (Georgia Institute of Technology)
–
Lunch
–
The Limits of Group Fairness and Predictive Multiplicity
Flavio Calmon (Harvard University)
–
Talk By
Flavio Calmon (Harvard University)
–
Privacy and Fairness in Collaborative AI
Yahya Hussain Essa (University of Southern California)
–
Privacy and Fairness in Collaborative AI
Salman Avestimehr (University of Southern California)
–
Coffee Break
–
Coffee Break
–
Poster Session (Click to view Presenters & Topics)
–
Light Breakfast and Check-In
–
Light Breakfast and Check-In
–
KEYNOTE: Robustness & Privacy and Wasserstein GANs topic (if not then Communicaiton Efficiency and Privacy in FL)
Ayfer Ozgur (Stanford University)
–
KEYNOTE: Information Constrained Optimal Transport
Ayfer Ozgur (Stanford University)
–
Coffee Break
–
Distribution estimation with user-level privacy and communication constraints
Jayadev Acharya (Cornell University)
–
Distribution estimation with user-level privacy and communication constraints
Jayadev Acharya (Cornell University)
–
Memorization in Machine Learning
Adam Smith (Boston University)
–
Memorization in Machine Learning
Adam Smith (Boston University)
–
Data Valuation: A Perturbation-Aware Approach
Giulia Fanti (Carnegie Mellon University)
–
Data Valuation: A Perturbation-Aware Approach
Giulia Fanti (Carnegie Mellon University)
–
Lunch
–
Lunch
–
Talk By
Ahmad Beirami (Google Research)
–
Differentially Quantized Gradient Methods
Victoria Kostina (California Institute of Technology)
–
Learning classification metrics from preference feedback
Sanmi Koyejo (Stanford University)
–
Learning classification metrics from preference feedback
Sanmi Koyejo (Stanford University)
–
Coffee Break
–
Overparameterized learning: an asymptotic toy model that shows interesting phenomena
Anant Sahai (UC Berkeley)
–
Overparameterized learning: an asymptotic toy model that shows interesting phenomena
Anant Sahai (UC Berkeley)
–
Information-Theoretic Methods for Fair Risk Minimization
Ahmad Beirami (Google Research)
–
Learning Under Data Poisoning
Amin Karbasi (Yale University)
–
Learning Under Data Poisoning
Amin Karbasi (Yale University)