activity
20062026
most citedPrivacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

5 citations · 21 across the 17 of their papers we have counts for

collaborators
Showing 2020Show all

9 papers · 1 filter

cs.LG20203 cited

Asymptotic Convergence of Thompson Sampling

Cem Kalkanli, Ayfer Ozgur

Thompson sampling has been shown to be an effective policy across a variety of online learning tasks. Many works have analyzed the finite time performance of Thompson sampling, and…

cs.IT2020

Strong Privacy and Utility Guarantee: Over-the-Air Statistical Estimation

Wenhao Zhan

We consider the privacy problem of statistical estimation from distributed data, where users communicate to a central processor over a Gaussian multiple-access channel(MAC). To avo…

cs.IT20202 cited

Information Constrained Optimal Transport: From Talagrand, to Marton, to Cover

Yikun Bai, Xiugang Wu, Ayfer Ozgur

The optimal transport problem studies how to transport one measure to another in the most cost-effective way and has wide range of applications from economics to machine learning.…

cs.LG2020

Breaking the Communication-Privacy-Accuracy Trilemma

Wei-Ning Chen, Peter Kairouz, Ayfer Özgür

Two major challenges in distributed learning and estimation are 1) preserving the privacy of the local samples; and 2) communicating them efficiently to a central server, while ach…

math.OC2020

Lower Bounds and a Near-Optimal Shrinkage Estimator for Least Squares using Random Projections

Srivatsan Sridhar, Mert Pilanci, Ayfer Özgür

In this work, we consider the deterministic optimization using random projections as a statistical estimation problem, where the squared distance between the predictions from the e…

cs.IT2020

Fisher information under local differential privacy

Leighton Pate Barnes, Wei-Ning Chen, Ayfer Ozgur

We develop data processing inequalities that describe how Fisher information from statistical samples can scale with the privacy parameter under local differential pr…