activity
20062022
most citedHadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communication

97 citations · 543 across the 40 of their papers we have counts for

collaborators

43 papers

cs.LG2022★ 7 cited

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

Jimmy Z. Di, Jack Douglas, Jayadev Acharya +2

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An ad…

cs.LG2022★ 1 cited

Discrete Distribution Estimation under User-level Local Differential Privacy

Jayadev Acharya, Yuhan Liu, Ziteng Sun

We study discrete distribution estimation under user-level local differential privacy (LDP). In user-level -LDP, each user has samples and the privacy of all $…

cs.DS2022★ 3 cited

The Role of Interactivity in Structured Estimation

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

We study high-dimensional sparse estimation under three natural constraints: communication constraints, local privacy constraints, and linear measurements (compressive sensing). Wi…

cs.DS2021★ 1 cited

Robust Estimation for Random Graphs

Jayadev Acharya, Ayush Jain, Gautam Kamath +2

We study the problem of robustly estimating the parameter of an Erdős-Rényi random graph on nodes, where a fraction of nodes may be adversarially corrupted. After showi…

math.ST2021

Optimal Rates for Nonparametric Density Estimation under Communication Constraints

Jayadev Acharya, Clément L. Canonne, Aditya Vikram Singh +1

We consider density estimation for Besov spaces when each sample is quantized to only a limited number of bits. We provide a noninteractive adaptive estimator that exploits the spa…

cs.IT2021

Principal Bit Analysis: Autoencoding with Schur-Concave Loss

Sourbh Bhadane, Aaron B. Wagner, Jayadev Acharya

We consider a linear autoencoder in which the latent variables are quantized, or corrupted by noise, and the constraint is Schur-concave in the set of latent variances. Although fi…