Temporal Quilting for Survival Analysis

The importance of survival analysis in many disciplines (especially in medicine) has led to the development of a variety of approaches to modeling the survival function. Models constructed via various approaches oer dierent strengths and weaknesses in terms of discriminative performance and calibration, but no one model is best across all datasets or even across all time horizons within a single dataset. Because we require both good calibration and good discriminative performance over dierent time horizons, conventional model selection and ensemble approaches are not applicable. This paper develops a novel approach that combines the collective intelligence of different underlying survival models to produce a valid survival function that is well-calibrated and oers superior discriminative performance at dierent time horizons. Empirical results show that our approach provides signicant gains over the benchmarks on a variety of real-world datasets.