Areas of Expertise (8)
Probability and Stochastic Processes
Malik Magdon-Ismail, a professor of computer science at Rensselaer Polytechnic Institute, is an expert in learning from data and decision-making in complex data systems. In his work, Magdon-Ismail mixes theory with validation through experiment or practice.
During the COVID-19 pandemic, he developed algorithms predicting aspects of the pandemic in small cities and school campuses. COVID War Room predicts the spread and severity of COVID-19 in small cities and counties through the United States and in select international locations. Building on the predictive power of the COVID War Room algorithms, Magdon-Ismail built COVID Back-to-School, a series of algorithms that make it possible to quantify the impacts of policy choices on the spread of COVID in a campus environment.
Other work include contributions to an intriguing project modeling stellar tidal streams from galactic collisions, mathematical models for optimal decision in a representative democracy, separating terrorist-like topological signatures embedded in benign networks, and understanding supercomputer failures using neuromorphic computing.
Yale University: B.S., Physics
California Institute of Technology: M.S., Physics
California Institute of Technology: Ph.D., Electrical Engineering
Media Appearances (5)
How Your Brain Functions in Certain Ways Could Be Key to Quantum Computing
The mysterious actions of quantum mechanics may be at work within your brain, and recent research supporting the idea could lead to improved quantum computers. A new study published in the peer-reviewed Journal of Physics Communications suggests that the human brain has much in common with a quantum computer. Experts say it's part of a growing body of evidence that quantum mechanisms could explain how the brain works. "Understanding quantum computing and the associated algorithms could reveal some of the deeper workings in the brain," Malik Magdon-Ismail, a professor of computer science at Rensselaer Polytechnic Institute, told Lifewire in an email interview.
How RPI fought the coronavirus and won
Times Union online
Aggressive testing strategy and algorithm helped keep COVID-19 at bay, university officials say
RPI launches ‘COVID Back to School’ response aid app
The more you know, the better you plan. The better you plan, the more likely you keep COVID-19 at bay. That’s the idea behind an all-new app Rensselaer Polytechnic Institute released on Thursday: “COVID Back to School.
RPI Develops App to Limit COVID Spread
Spectrum News online
Rensselaer Polytechnic Institute hasn’t had some of the COVID-19 problems other college campuses have and those at the school credit an algorithm and app for keeping cases to a minimum.
An Update On RPI's COVID-19 Model And The Coming "War"
We get an update from Dr. Malik Magdon-Ismail, Professor of Computer Science at RPI, who has been working on a machine learning model for predicting the impacts of the pandemic.
AI and ML for Predicting COVID-19AAAI Symposium on AI for Social Good
Keynote address on using AL and machine learning for predicting spread of COVID-19.
Machine Learning the Phenomenology of COVID-19 From Early Infection DynamicsarXiv
We present a robust data-driven machine learning analysis of the COVID-19 pandemic from its early infection dynamics, specifically infection counts over time. The goal is to extract actionable public health insights. These insights include the infectious force, the rate of a mild infection becoming serious, estimates for asymtomatic infections and predictions of new infections over time. We focus on USA data starting from the first confirmed infection on January 20 2020. Our methods reveal significant asymptomatic (hidden) infection, a lag of about 10 days, and we quantitatively confirm that the infectious force is strong with about a 0.14% transition from mild to serious infection. Our methods are efficient, robust and general, being agnostic to the specific virus and applicable to different populations or cohorts.
Nonlinear Dynamics from Incomplete NetworksAAAI
Chunheng Jiang, Jianxi Gao, Malik Magdon-Ismail
We study nonlinear dynamics on complex networks. Each vertex i has a state xi which evolves according to a networked dynamics to a steady-state x ∗i. We develop fundamental tools to learn the true steady-state of a small part of the network, without knowing the full network. A naive approach and the current state-of-the-art is to follow the dynamics of the observed partial network to local equilibrium. This dramatically fails to extract the true steady state. We use a mean-field approach to map the dynamics of the unseen part of the network to a single node, which allows us to recover accurate estimates of steady-state on as few as 5 observed vertices in domains ranging from ecology to social networks to gene regulation. Incomplete networks are the norm in practice, and we offer new ways to think about nonlinear dynamics when only sparse information is available.