aiqbench analysis
This research proposes a novel survival analysis algorithm leveraging Reinforcement Learning principles, specifically Deep Q-Networks, to enhance temporal consistency in longitudinal data modeling. By introducing delayed target networks, the method achieves more stable training and superior performance on long-sequence datasets compared to standard baselines. The work advances machine learning techniques for handling complex temporal dependencies within large-scale predictive frameworks.
Deep End-to-End Survival Analysis with Temporal Consistency
arXiv:2410.06786v2 Announce Type: replace Abstract: In this study, we present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. Our approach draws inspiration from Reinforcement Learning principles, particularly the Deep Q-Network paradigm, extending Temporal Learning concepts to Survival Regression. A central argument in our method relies on temporal consistency, a recursive consistency condition between survival predictions made at consecutive states. Our framework introduces a delayed target network that decouples the generation of temporally consistent training targets from model updates, providing a more stable training signal while enabling mini-batch optimization and end-to-end training. Additionally, it supports arbitrarily complex architectures, enabling the modeling of intricate temporal dependencies. Through numerous experiments we provide empirical evidence demonstrating our framework's ability to exploit temporal consistency across datasets of varying sizes. Moreover, our algorithm outperforms benchmarks on datasets with long sequences, demonstrating its ability to capture long-term patterns. Finally, ablation studies show that the degree of target delay has a substantial effect on predictive performance and training variability. Across two distinct survival model families, delayed target updates consistently improve over the same-timescale baseline.
Abstract:In this study, we present a novel Survival Analysis algorithm designed to efficiently handle large-scale longitudinal data. Our approach draws inspiration from Reinforcement Learning principles, particularly the Deep Q-Network paradigm, extending Temporal Learning concepts to Survival Regression. A central argument in our method relies on temporal consistency, a recursive consistency condition between survival predictions made at consecutive states. Our framework introduces a delayed target network that decouples the generation of temporally consistent training targets from model updates, providing a more stable training signal while enabling mini-batch optimization and end-to-end training. Additionally, it supports arbitrarily complex architectures, enabling the modeling of intricate temporal dependencies. Through numerous experiments we provide empirical evidence demonstrating our framework's ability to exploit temporal consistency across datasets of varying sizes. Moreover, our algorithm outperforms benchmarks on datasets with long sequences, demonstrating its ability to capture long-term patterns. Finally, ablation studies show that the degree of target delay has a substantial effect on predictive performance and training variability. Across two distinct survival model families, delayed target updates consistently improve over the same-timescale baseline.
Machine Learning (cs.LG)
arXiv:2410.06786 [cs.LG]
(or arXiv:2410.06786v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2410.06786 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 267 words
Related coverage
SurvCF(t): Counterfactual Explanations for Survival Analysis in Predictive Maintenance Multivariate Time Series Data
arXiv · Jul 21, 2026
NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress
arXiv · Aug 24, 2026
Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients
arXiv · Sep 22, 2026
DynSHAP: Towards Explainable Dynamic Survival Analysis
arXiv · Sep 14, 2026