We design new algorithms that leverage tools from survival analysis to provably perform well in these settings. We demonstrate the value of our approach on a large-scale clinical trial database on metastatic breast cancer.…Read More
This project adapts online learning techniques to unstructured data, focusing on neural networks. We posit a non-parametric multi-armed bandit algorithm with context that uses a neural network for its underlying function approximation. We theoretically analyze and prove guarantees on the regret under this algorithm…Read More
In this paper, we propose combining data from both surrogate and true outcomes to improve decision-making within a late-phase clinical trial.…Read More
This proposal requests research funding for the development of two papers that propose novel methods for leveraging large amounts of imprecise information along with small amounts of specific information to improve the efficacy of medical treatment. …Read More
