Portrait of Amin Emad

Amin Emad

Associate Academic Member
Assistant Professor, McGill University, Department of Electrical and Computer Engineering
Research Topics
Causality
Computational Biology
Deep Learning
Generative Models
Graph Neural Networks
Learning on Graphs
Molecular Modeling
Multimodal Learning
Probabilistic Models
Representation Learning

Biography

Amin Emad is an assistant professor in the Department of Electrical and Computer Engineering at McGill University and an associate academic member of Mila – Quebec Artificial Intelligence Institute.

He is affiliated with McGill’s Rosalind and Morris Goodman Cancer Institute, the McGill initiative in Computational Medicine (MiCM), McGill’s Quantitative Life Sciences (QLS) program, and the Meakins-Christie Laboratories at the McGill University Hospital Centre.

Before joining McGill, Emad was a postdoctoral research associate at the NIH-funded KnowEnG – A Center of Excellence in Big Data Computing, which is associated with the Department of Computer Science and the Institute for Genomic Biology at the University of Illinois at Urbana-Champaign (UIUC). He received his PhD from UIUC in 2015, his MSc from the University of Alberta in 2009, and his BSc from Sharif University of Technology (Tehran) in 2007. Emad’s research lies at the intersection of AI and computational biology.

Current Students

Shayan Hajhashemi
PhD - McGill University
Github
David Earl Hostallero
PhD - McGill University
William Ma
Master's Research - McGill University
Github
Safyan Aman Memon
Master's Research - McGill University
Google Scholar
Ali Saberi
PhD - McGill University
Cedrique Shum-Tim
PhD - McGill University
Github
Kiri Stern
PhD - McGill University
Chen Su
PhD - McGill University
Joseph Szymborski
PhD - McGill University
Website
Github
Yazdan Zinati
Master's Research - McGill University
hi@yazdan.me
Website
Github
Google Scholar

Publications

Poisson Group Testing: A Probabilistic Model for Boolean Compressed Sensing
Amin Emad
Olgica Milenkovic
We introduce a novel probabilistic group testing framework, termed Poisson group testing, in which the number of defectives follows a right-… (see more)truncated Poisson distribution. The Poisson model has a number of new applications, including dynamic testing with diminishing relative rates of defectives. We consider both nonadaptive and semi-adaptive identification methods. For nonadaptive methods, we derive a lower bound on the number of tests required to identify the defectives with a probability of error that asymptotically converges to zero; in addition, we propose test matrix constructions for which the number of tests closely matches the lower bound. For semiadaptive methods, we describe a lower bound on the expected number of tests required to identify the defectives with zero error probability. In addition, we propose a stage-wise reconstruction algorithm for which the expected number of tests is only a constant factor away from the lower bound. The methods rely only on an estimate of the average number of defectives, rather than on the individual probabilities of subjects being defective.
2014-10-20
ArXiv (preprint)
doi.org
arxiv.org