A1259
Title: Nonparametric survival estimation with time-varying covariates using neural networks
Authors: Bin Nan - University of California, Irvine (United States) [presenting]
Abstract: Traditional survival models often assume instantaneous effects of time-varying covariates on the hazard function, which can be restrictive. We consider nonparametric estimation of the conditional survival function, which leverages the flexibility of neural networks to capture the complex, potentially long-term effects of time-varying covariates on the hazard function. We introduce the use of deep operator neural networks, a deep learning architecture designed for operator learning, to model arbitrary effects of both time-varying and time-invariant covariates.
