activity
20172021
collaborators

10 papers

stat.ML2021

Distributed Sparse Feature Selection in Communication-Restricted Networks

Hanie Barghi, Amir Najafi, Seyed Abolfazl Motahari

This paper aims to propose and theoretically analyze a new distributed scheme for sparse linear regression and feature selection. The primary goal is to learn the few causal featur…

cs.CL2020

Regularizing Recurrent Neural Networks via Sequence Mixup

Armin Karamzade, Amir Najafi, Seyed Abolfazl Motahari

In this paper, we extend a class of celebrated regularization techniques originally proposed for feed-forward neural networks, namely Input Mixup (Zhang et al., 2017) and Manifold…

cs.IT2019

Private Shotgun DNA Sequencing: A Structured Approach

Ali Gholami, Mohammad Ali Maddah-Ali, Seyed Abolfazl Motahari

DNA sequencing has faced a huge demand since it was first introduced as a service to the public. This service is often offloaded to the sequencing companies who will have access to…

cs.LG2018

Structure Learning of Sparse GGMs over Multiple Access Networks

Mostafa Tavassolipour, Armin Karamzade, Reza Mirzaeifard +2

A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The loca…

math.ST2018

Information Theoretic Bounds on Optimal Worst-case Error in Binary Mixture Identification

Khashayar Gatmiry, Seyed Abolfazl Motahari

Identification of latent binary sequences from a pool of noisy observations has a wide range of applications in both statistical learning and population genetics. Each observed seq…

q-bio.GN2018

Private Shotgun DNA Sequencing

Ali Gholami, Mohammad Ali Maddah-Ali, Seyed Abolfazl Motahari

Current techniques in sequencing a genome allow a service provider (e.g. a sequencing company) to have full access to the genome information, and thus the privacy of individuals re…