Survival Analysis via Density Estimation

Hiroki Yanagisawa, Shunta Akiyama

Keywords: survival analysis, censored regression, competing risks, dependent censoring

Abstract: This paper introduces an algorithm that reinterprets survival analysis through the lens of density estimation, addressing the challenge of censored inputs inherent to survival data. Recognizing that many survival analysis methodologies are extensions of foundational density estimation models, our approach leverages this intrinsic relationship. By conceptualizing survival analysis as a form of density estimation, our algorithm postprocesses the density estimation outputs to derive survival functions. This framework allows for the application of any density estimation model to effectively estimate survival functions, thereby broadening the toolkit available for survival analysis and enhancing the flexibility and applicability of existing density estimation techniques in this domain. The proposed algorithm not only bridges the methodological gap between density estimation and survival analysis but also offers a versatile and robust approach for handling censored survival data.

Primary Area: other topics in machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 9624