Pre-Recorded Talks

Talks will continue to be updated as we get closer to the workshop.

Adam Dziedzic, Vector Institute / University of Toronto
CaPC Learning: Confidential and Private Collaborative Learning

Anastasios Kyrillidis, Rice CS
Distributed neural network training via independent subnets

Antti Honkela, University of Helsinki / FCAI
Locally Differentially Private Bayesian Inference

Aritra Mitra, University of Pennsylvania
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients

Ashwinee Panda
SparseFed: Mitagation Model Poisining Attacks in Federated Learning with Sparsification

Aurélien Bellet, INRIA
Federated Multi-Task Learning under a Mixture of Distributions 

Carolina Naim, Rutgers University
Private Multi-Group Aggregation

Clement Canonne, University of Sydney
Private Goodness-of-Fit: a few ideas go a long way

Edwige Cyffers, INRIA
Privacy Amplification by Decentralization

Emiliano De Cristofaro, University College London
Experimenting with Local and Central Differential Privacy for Both Robustness and Privacy in Federated Learning 

Gautam Kamath, University of Waterloo
Differentially Private Fine-tuning of Language Models

Gavin Brown, Boston University
When is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?

Hanieh Hashemi, University of Southern California
FedVault: Efficient Gradient Outlier Detection for Byzantine-Resilient and Privacy-Preserving FedML

Jayadev Acharya, Cornell University
Information-constrained optimization: can adaptive processing of gradients help?

Jiayuan Ye, National University of Singapore
Differential privacy dynamics of noisy gradient descent

Jonathan Hehir & Aleksandra Slavkovic, Penn State
Consistent Spectral Clustering of Network Block Models under Local Differential Privacy

Ken Liu (with Naman Agarwal and Peter Kairouz)
The Skellam Mechanism for Differentially Private Federated Learning

Krishna Pillutla, University of Washington
Statistical Heterogeneity in Federated Learning

Leighton Pate Barnes, Stanford University
Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning with Model Averaging

Mikko Heikkilä, University of Helsinki
Tight Accounting in the Shuffle Model of Differential Privacy

Phillipp Schoppmann, Google
Distributed Point Functions: Efficient Secure Aggregation and Beyond with Non-Colluding Servers

Salim El Rouayheb, Rutgers University
How to Turn Privacy ON and OFF and ON Again

Samuel Horvath, King Abdullah University of Science and Technology
Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout

Saurabh Bagchi
Secure Federated Learning on Wimpy Devices

Sebastian Stich, EPFL
Gaps between FL optimization theory and practice

Wenjun Hu, Yale University
Mistify: Automating DNN Model Porting for On-Device Inference at the Edge

Yanning Shen, University of California, Irvine
Personalized Graph-Aided Online Federated Model Selection

Ziteng Sun, Cornell University
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition