Partial Likelihood Thompson Sampling
This addresses vaccine allocation challenges in public health, but it is incremental as it adapts existing Thompson sampling to a specific domain.
The paper tackles the problem of targeting and prioritizing existing vaccines against new disease variants by developing partial likelihood Thompson sampling to handle delayed feedback and varying prevalence, achieving a method tested on 200 days of COVID-19 infection data in a semi-synthetic experiment.
We consider the problem of deciding how best to target and prioritize existing vaccines that may offer protection against new variants of an infectious disease. Sequential experiments are a promising approach; however, challenges due to delayed feedback and the overall ebb and flow of disease prevalence make available methods inapplicable for this task. We present a method, partial likelihood Thompson sampling, that can handle these challenges. Our method involves running Thompson sampling with belief updates determined by partial likelihood each time we observe an event. To test our approach, we ran a semi-synthetic experiment based on 200 days of COVID-19 infection data in the US.