Privacy papers in AISTATS 2021

1 minute read

Published:

I have curated and am beginning to read AISTATS ‘21 papers related to privacy. The list will be constantly updated with the paper summaries. Stay tuned!
Note that I wrote a simple script to scrape the ArXiv links to the paper and the links may not be accurate.

TitleSummary
Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning 
Differentially Private Analysis on Graph Streams 
Differentially Private Online Submodular Maximization 
On the Privacy Properties of GAN-generated Samples 
Robust and Private Learning of Halfspaces 
DP-MERF: Differentially Private Mean Embeddings with RandomFeatures for Practical Privacy-preserving Data Generation 
Stability and Differential Privacy of Stochastic Gradient Descent for Pairwise Learning with Non-Smooth Loss 
No-Regret Algorithms for Private Gaussian Process Bandit Optimization 
Federated f-Differential Privacy 
Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models 
Optimal query complexity for private sequential learning against eavesdropping 
Differentially Private Weighted Sampling 
Shuffled Model of Differential Privacy in Federated Learning 
Private optimization without constraint violations 
Evading the Curse of Dimensionality in Unconstrained Private GLMs 
Location Trace Privacy Under Conditional Priors 
Differentially Private Monotone Submodular Maximization Under Matroid and Knapsack Constraints 
Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT