# Online Survival Analysis: A Bandit Approach under Cox PH Model

arXiv: https://arxiv.org/abs/2604.20296 · HTML: https://mlsanity.com/paper/2604.20296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 42 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling](https://mlsanity.com/paper/2006.04012/) (2020)
- [Generalized Linear Bandits with Local Differential Privacy](https://mlsanity.com/paper/2106.03365/) (2021)
- [Contextual Linear Bandits with Delay as Payoff](https://mlsanity.com/paper/2502.12528/) (2025)
- [Delay as Payoff in MAB](https://mlsanity.com/paper/2408.15158/) (2024)
- [Weibull Racing Survival Analysis with Competing Events, Left Truncation, and Time-varying Covariates](https://mlsanity.com/paper/1911.01827/) (2019)

## Abstract (arXiv)

Survival analysis is a widely used statistical framework for modeling time-to-event data under censoring. Classical methods, such as the Cox proportional hazards (Cox PH) model, offer a semiparametric approach to estimating the effects of covariates on the hazard function. Despite its importance, survival analysis has been largely unexplored in online settings, particularly within the bandit framework, where decisions must be made sequentially to optimize treatments as new data arrive over time. In this work, we take an initial step toward integrating survival analysis into a purely online learning setting under the Cox PH model, addressing key challenges including staggered entry, delayed feedback, and right censoring. We adapt three canonical bandit algorithms to balance exploration and exploitation, with theoretical guarantees of sublinear regret bounds. Extensive simulations and semi-real experiments using SEER cancer data demonstrate that our approach enables rapid and effective learning of near-optimal treatment policies.