activity
20162022
most citedUnified lower bounds for interactive high-dimensional estimation under information constraints

8 citations · 14 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2022★ 2 cited

Continual Mean Estimation Under User-Level Privacy

Anand Jerry George, Lekshmi Ramesh, Aditya Vikram Singh +1

We consider the problem of continually releasing an estimate of the population mean of a stream of samples that is user-level differentially private (DP). At each time instant, a u…

cs.IT2021★ 4 cited

Multiple Support Recovery Using Very Few Measurements Per Sample

Lekshmi Ramesh, Chandra R. Murthy, Himanshu Tyagi

In the problem of multiple support recovery, we are given access to linear measurements of multiple sparse samples in . These samples can be partitioned into …

cs.IT2020

Wyner-Ziv Estimators for Distributed Mean Estimation with Side Information and Optimization

Prathamesh Mayekar, Shubham Jha, Ananda Theertha Suresh +1

Communication efficient distributed mean estimation is an important primitive that arises in many distributed learning and optimization scenarios such as federated learning. Withou…

cs.DS2020★ 8 cited

Unified lower bounds for interactive high-dimensional estimation under information constraints

Jayadev Acharya, Clément L. Canonne, Ziteng Sun +1

We consider distributed parameter estimation using interactive protocols subject to local information constraints such as bandwidth limitations, local differential privacy, and res…

cs.DS2020

Interactive Inference under Information Constraints

Jayadev Acharya, Clément L. Canonne, Yuhan Liu +2

We study the role of interactivity in distributed statistical inference under information constraints, e.g., communication constraints and local differential privacy. We focus on t…

cs.IT2020

Tracking an Auto-Regressive Process with Limited Communication per Unit Time

Rooji Jinan, Parimal Parag, Himanshu Tyagi

Samples from a high-dimensional AR[1] process are observed by a sender which can communicate only finitely many bits per unit time to a receiver. The receiver seeks to form an esti…