69 citations · 116 across the 31 of their papers we have counts for
26 papers · 1 filter
Local and Global Contraction Principles for MCMC Mixing
Alireza Daeijavad, Shahab Asoodeh
We develop a contraction-based framework for proving mixing-time bounds for Markov chain Monte Carlo algorithms. The framework is built around global and local contraction coeffici…
Learning from Totally Unpaired Data via Minimum Conditional Entropy Coupling
Shahab Asoodeh, Cheuk Ting Li, Jun Chen
Consider an "unsupervised classification" setting, where the goal is to learn a predictor of the categorical class variable using the categorical feature variables $Y_1,\ldots,…
Optimality of Staircase Mechanisms for Vector Queries under Differential Privacy
James Melbourne, Mario Diaz, Shahab Asoodeh
We study the optimal design of additive mechanisms for vector-valued queries under -differential privacy (DP). Given only the sensitivity of a query and a norm-monotone cost fun…
Optimizing Noise Distributions for Differential Privacy
Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh +3
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP,…
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…
Contraction of Locally Differentially Private Mechanisms
Shahab Asoodeh, Huanyu Zhang
We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between and outp…