2 papers
cs.LG2023
Hot PATE: Private Aggregation of Distributions for Diverse Task
Edith Cohen, Benjamin Cohen-Wang, Xin Lyu +3
The Private Aggregation of Teacher Ensembles (PATE) framework enables privacy-preserving machine learning by aggregating responses from disjoint subsets of sensitive data. Adaptati…
cs.DS2022
Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive Inputs
Edith Cohen, Jelani Nelson, Tamás Sarlós +1
CountSketch and Feature Hashing (the "hashing trick") are popular randomized dimensionality reduction methods that support recovery of -heavy hitters (keys where $v_i^2…