Poster
in
Workshop: Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice

The Limits to Learning a Diffusion Model

Jackie Baek · Vivek Farias · ANDREEA GEORGESCU · Retsef Levi · Tianyi Peng · Joshua Wilde · Andrew Zheng


Abstract:

This paper provides the first sample complexity lower bounds for the estimation of simple diffusion models, including the Bass model (used in modeling consumer adoption) and the SIR model (used in modeling epidemics). We show that one cannot hope to learn such models until quite late in the diffusion. Specifically, we show that the time required to collect a number of observations that exceeds our sample complexity lower bounds is large. For Bass models with low innovation rates, our results imply that one cannot hope to predict the eventual number of adopting customers until one is at least two-thirds of the way to the time at which the rate of new adopters is at its peak. In a similar vein, our results imply that in the case of an SIR model, one cannot hope to predict the eventual number of infections until one is approximately two-thirds of the way to the time at which the infection rate has peaked. These limits are borne out in both product adoption data (Amazon), as well as epidemic data (COVID-19).

Chat is not available.