69 citations · 116 across the 31 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
stat.ML2023
Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
Alireza F. Pour, Hassan Ashtiani, Shahab Asoodeh
We study the problem of hypothesis selection under the constraint of local differential privacy. Given a class of distributions and a set of i.i.d. samples from a…
cs.LG2023
Privacy Loss of Noisy Stochastic Gradient Descent Might Converge Even for Non-Convex Losses
Shahab Asoodeh, Mario Diaz
The Noisy-SGD algorithm is widely used for privately training machine learning models. Traditional privacy analyses of this algorithm assume that the internal state is publicly rev…
cs.IT2023★ 3 cited
The Cardinality Bound on the Information Bottleneck Representations is Tight
Etam Benger, Shahab Asoodeh, Jun Chen
The information bottleneck (IB) method aims to find compressed representations of a variable that retain the most relevant information about a target variable . We show that…