activity
20192021
most citedPrivacy-Preserving Distributed Learning in the Analog Domain

11 citations · 11 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2021

ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems

Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar +1

Due to the surge of cloud-assisted AI services, the problem of designing resilient prediction serving systems that can effectively cope with stragglers/failures and minimize respon…

cs.IT2021

Coded Computing via Binary Linear Codes: Designs and Performance Limits

Mahdi Soleymani, Mohammad Vahid Jamali, Hessam Mahdavifar

We consider the problem of coded distributed computing where a large linear computational job, such as a matrix multiplication, is divided into smaller tasks, encoded using an…

cs.IT2021

List-Decodable Coded Computing: Breaking the Adversarial Toleration Barrier

Mahdi Soleymani, Ramy E. Ali, Hessam Mahdavifar +1

We consider the problem of coded computing, where a computational task is performed in a distributed fashion in the presence of adversarial workers. We propose techniques to break…

cs.IT2020

Analog Lagrange Coded Computing

Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

A distributed computing scenario is considered, where the computational power of a set of worker nodes is used to perform a certain computation task over a dataset that is disperse…

cs.LG202011 cited

Privacy-Preserving Distributed Learning in the Analog Domain

Mahdi Soleymani, Hessam Mahdavifar, A. Salman Avestimehr

We consider the critical problem of distributed learning over data while keeping it private from the computational servers. The state-of-the-art approaches to this problem rely on…

cs.IT2019

Coded Distributed Computing: Performance Limits and Code Designs

Mohammad Vahid Jamali, Mahdi Soleymani, Hessam Mahdavifar

We consider the problem of coded distributed computing where a large linear computational job, such as a matrix multiplication, is divided into smaller tasks, encoded using an…