Metraipolis › archive › dc_df7c7cdbac1c
Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization — arXiv:2609.25013
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25013
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:44:47.125Z
- SHA-256 of the archived text
9bc2caf653f344947b43cb4cd25e422f7dd9d189511f5c97f532e37c7b7a01f8- Stable URL of this page
https://metraipolis.com/documento/dc_df7c7cdbac1c
How to cite
Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization — arXiv:2609.25013 — arXiv (en), https://arxiv.org/abs/2609.25013 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df7c7cdbac1c (Metraipolis archive dc_df7c7cdbac1c, sha256 9bc2caf653f344947b43cb4cd25e422f7dd9d189511f5c97f532e37c7b7a01f8)
BibTeX
@misc{dcdf7c7cdbac1c,
title = {Do Existing Preconditioners Improve Biomedical Tabular Foundation Learning? An Empirical Study on TabPFN Optimization — arXiv:2609.25013},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25013},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df7c7cdbac1c; sha256 9bc2caf653f344947b43cb4cd25e422f7dd9d189511f5c97f532e37c7b7a01f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25013. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tabular foundation models have recently shown strong potential for structured biomedical data analysis. Among them, TabPFN has emerged as an effective approach for low-data tabular classification tasks. However, the impact of optimization and preconditioning strategies on biomedical fine-tuning remains largely unexplored. In this work, we present a comprehensive empirical investigation of five AdamW-based preconditioning strategies for fine-tuning TabPFN v2.5 on 59 biomedical datasets spanning Alzheimer's disease, breast cancer, schizophrenia, significant memory concern (SMC), KEEL biomedical datasets, and UCI biomedical benchmarks. The evaluation considers predictive performance, computational efficiency, and statistical significance analysis. Experimental results demonstrate that the original AdamW optimizer consistently achieves the best overall performance and statistical ranking, while existing curvature-aware preconditioners fail to provide reliable improvements across diverse biomedical learning scenarios. The findings suggest that generic preconditioning approaches may not adequately capture the optimization characteristics of biomedical tabular learning, motivating the development of biomedical-aware preconditioners specifically tailored for healthcare-oriented tabular foundation models. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.25013 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:18:38.052Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).