Temporally-Consistent Survival Analysis

Abstract

We study survival analysis in the dynamic setting: We seek to model the time to an event of interest given sequences of states. Taking inspiration from temporal-difference learning, a central idea in reinforcement learning, we develop algorithms that estimate a discrete-time survival model by exploiting a temporal-consistency condition. Intuitively, this condition captures the fact that the survival distribution at consecutive states should be similar, accounting for the delay between states. Our method can be combined with any parametric survival model and naturally accommodates right-censored observations. We demonstrate empirically that it achieves better sample-efficiency and predictive performance compared to approaches that directly regress the observed survival outcome.

Related

March 2023 | Frontier on Big Data: Recommender Systems

A Survey on Multi-objective Recommender Systems

Dietmar Jannach and Himan Abdollahpouri

March 2023 | Nature Machine Intelligence

Estimating categorical counterfactuals via deep twin networks

Athanasios Vlontzos, Bernhard Kainz, Ciarán M. Gilligan-Lee

March 2023 | Intelligent User Interfaces (IUI)

Enabling Goal-Focused Exploration of Podcasts in Interactive Recommender Systems

Yu Liang, Aditya Ponnada, Paul Lamere, Nediyana Daskalova