Location: Room Ypsilon IV-V-VI

8:30 – 9:00   Breakfast and coffee

9:00 – 10:00  Tutorial I: Peter Kairouz (Google) 

10:00 – 10:15 Break

10:15 – 10:45 Lightning presentations (Spotlight): 

• Information-Theoretical Bounds on Privacy Leakage in Pruned Federated Learning, Tianyue Chu, Mengwei Yang, Nikolaos Laoutaris, Athina Markopoulou

• Adapting Differentially Private Synthetic Data to Relational Databases, Kaveh Alimohammadi, Hao Wang, Ben Reilly, Akash Srivastava, Navid Azizan

• Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition, Faisal Hamman, Sanghamitra Dutta

10:45 – 12:15 Invited talks I: 

Sanghamitra Dutta (UMD): Information-theoretic Methods in Explainability for High-Stakes Applications

Catuscia Palamidessi (Inria Saclay and LIX): Information Structures for Privacy and Fairness

Mario Diaz (UNAM): On the Differential Privacy Guarantees of Iterative Training Algorithms

12:15 – 1:00  Lunch 

1:00 – 2:45   Poster Session

2:45 – 3:45   Tutorial II: Kush Varshney (IBM): The AI Alignment Problem, Solutions, and Limits

3:45 – 4:00   Break

4:00 – 5:00   Invited talks II: 

Haewon Jeong (UCSB): Emerging Safety Issues in Generative Models

Ananda Suresh Theerta (Google): Improved Private Mean Estimation

List of accepted posters:

• • • • W2 – 1: User-Level Differentially Private Mean Estimation for Real-World Datasets, V. Arvind Rameshwar, Anshoo Tandon, Abhay Sharma

      • W2 – 20: No Bidding, No Regret: Pairwise Feedback Mechanisms for Digital Goods and Data Auctions, Zachary Robertson, Sanmi Koyejo

      • W2 – 3: Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition,  Faisal Hamman, Sanghamitra Dutta 

      • W2 – 18: Maverick-Aware Shapley Valuation for Client Selection in Federated Learning, Mengwei Yang, Ismat Jarin, Baturalp Buyukates, Salman Avestimehr, Athina Markopoulou

      • W2 – 5: Learning To Help: Training Models to Assist Legacy Devices, Yu Wu, Anand D. Sarwate

      • W2 – 6: Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms, Mehrdad Pournaderi, Yu Xiang

      • W2 – 16: Differentially Private Fair Binary Classifications, Hrad Ghoukasian, Shahab Asoodeh

      • W2 – 8: Information-Theoretical Bounds on Privacy Leakage in Pruned Federated Learning, Tianyue Chu, Mengwei Yang, Nikolaos Laoutaris, Athina Markopoulou

      • W2 – 15: Strong Data Processing Inequalities for Locally Differentially Private Mechanisms, Behnoosh Zamanlooy, Mario Diaz, Flavio Calmon, and Shahab Asoodeh

      • W2 – 10: Fairness-Enhancing Data Augmentation Methods for Worst-Group Accuracy, Monica Welfert, Nathan Stromberg, Lalitha Sankar

      • W2 – 11: Adapting Differentially Private Synthetic Data to Relational Databases, Kaveh Alimohammadi, Hao Wang, Ben Reilly, Akash Srivastava, Navid Azizan

      • W2 – 13: V-Fair Classifier: Analyzing Adversarially Fair Classifier from V-Information Perspective, Shelvia Wongso, Cheuk Ting Leung, Rohan Ghosh, Mehul Motani