activity
20112026
most citedDitto: Fair and Robust Federated Learning Through Personalization

219 citations · 513 across the 53 of their papers we have counts for

collaborators
Showing cs.ITShow all

28 papers · 1 filter

cs.IT2026

The Most Informative Bit and Beyond: A Proof of the Courtade--Kumar Conjecture and Multibit Extensions

Hessam Mahdavifar, Ahmad Beirami

Let \(X=(X_1,\ldots,X_n)\) be uniform on the Boolean cube, and let \(Y\) be obtained by passing its coordinates independently through a binary symmetric channel with crossover prob…

cs.IT2020

Centralized vs Decentralized Targeted Brute-Force Attacks: Guessing with Side-Information

Salman Salamatian, Wasim Huleihel, Ahmad Beirami +2

According to recent empirical studies, a majority of users have the same, or very similar, passwords across multiple password-secured online services. This practice can have disast…

cs.IT2019

Nonlinear Function Estimation with Empirical Bayes and Approximate Message Passing

Hangjin Liu, You, Zhou +2

Nonlinear function estimation is core to modern machine learning applications. In this paper, to perform nonlinear function estimation, we reduce a nonlinear inverse problem to a l…

cs.IT2019★ 4 cited

Mismatched Guesswork

Salman Salamatian, Litian Liu, Ahmad Beirami +1

We study the problem of mismatched guesswork, where we evaluate the number of symbols which have higher likelihood than according to a mismatched dis…

cs.IT2019

Universal Compression with Side Information from a Correlated Source

Ahmad Beirami, Faramarz Fekri

Packets originated from an information source in the network can be highly correlated. These packets are often routed through different paths, and compressing them requires to proc…

cs.IT2018

Information Bottleneck Methods for Distributed Learning

Parinaz Farajiparvar, Ahmad Beirami, Matthew Nokleby

We study a distributed learning problem in which Alice sends a compressed distillation of a set of training data to Bob, who uses the distilled version to best solve an associated…