Quanquan Gu, Assistant Professor of Computer Science, UCLA
Epidemic Model Guided Machine Learning for COVID-19 Forecasts
Abstract: The novel coronavirus disease (COVID-19) has emerged as a global pandemic, and caused over 910,000 deaths in the world. In this talk, I will introduce our project (https://covid19.uclaml.org) using an epidemic model-guided machine learning approach to understand and forecast the spread of COVID-19 and further facilitate the decision making of the government agencies. In specific, I will introduce our UCLA-SuEIR model, which is a variant of the SEIR model and takes into account the unreported cases of COVID-19. Our model can provide forecasts of COVID-19 confirmed cases and deaths, as well as hospital/ICU bed occupancy at county, state and national level. Our forecasts are being used by the Centers for Disease Control and Prevention (CDC) and California Department of Public Health (CDPH). Various performance evaluations indicate that our model is consistently among the top three forecast models used by CDC.
Biography: Quanquan Gu is an Assistant Professor of Computer Science at UCLA. His current research is in the area of artificial intelligence and machine learning, with a focus on developing and analyzing nonconvex optimization algorithms for machine learning and building the theoretical foundations of deep learning. He received his Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014. He is a recipient of the Yahoo! Academic Career Enhancement Award, NSF CAREER Award, Simons Berkeley Research Fellowship, Adobe Data Science Research Award, Salesforce Deep Learning Research Award and AWS Machine Learning Research Award. He is currently leading the COVID-19 modeling and forecasts team at UCLA. His team is working with the Centers for Disease Control and Prevention (CDC) to predict the spread of COVID-19. The model (UCLA SuEIR) developed by his team is one of the models used by the CDC for COVID-19 weekly cumulative deaths and hospitalization forecasts. His team is also working with the California Department of Public Health (CDPH) on the effective reproduction number and hospitalization forecasts in the counties of California.