Shift, Scale, and Restart Smaller Models to Estimate Larger Ones: Agent-Based Simulators for COVID Modeling
Speaker: Dr. Sandeep Juneja, Senior Professor at the Tata Institute of Fundamental Research
Abstract: Agent-based simulators are a popular epidemiological modeling tool to study the impact of various non-pharmaceutical interventions in managing an evolving pandemic. They provide the flexibility to accurately model a heterogeneous population with time and location-varying, person-specific interactions. To accurately model detailed behavior, typically each person is separately modeled. This, however, may make computational time prohibitive when the region population is large and when time horizons involved are large. We observe that simply considering a smaller aggregate model and scaling up the output leads to inaccuracies. In this talk, we primarily focus on the COVID-19 pandemic and dig deeper into the underlying probabilistic structure of an associated agent-based simulator (ABS) to arrive at modifications that allow smaller models to give accurate statistics for larger models. We exploit the observations that in the initial disease spread phase, the starting infections behave like a branching process. Further, later once enough people have been infected, the infected population closely follows its mean field approximation. We build upon these insights to develop a shifted, scaled, and restart version of the simulator that accurately evaluates the ABS's performance using a much smaller model while essentially eliminating the bias that otherwise arises from smaller models.
Bio: Sandeep is a senior professor at the School of Technology and Computer Science at Tata Institute of Fundamental Research in Mumbai. His research interests lie in applied probability including sequential learning, financial mathematics, Monte Carlo methods, and game-theoretic analysis of queues. Lately, he has been involved in modeling COVID-19 spread in Mumbai, and studying the mathematics of agent-based simulation models. Sandeep received his B.Tech. from IIT Delhi and M.S. in Statistics and Ph.D. in Operations Research from Stanford University. He is currently on the editorial board of Stochastic Systems. Previously, he was on the editorial boards of Mathematics of Operations Research, Management Science, and ACM TOMACS.