Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909620909375488 |
|---|---|
| author | Jaiswal, Prateek Keyvanshokooh, Esmaeil Cao, Junyu |
| author_facet | Jaiswal, Prateek Keyvanshokooh, Esmaeil Cao, Junyu |
| contents | Randomized clinical trials often require large patient cohorts before drawing definitive conclusions, yet abundant observational data from parallel studies remains underutilized due to confounding and hidden biases. To bridge this gap, we propose Deconfounded Warm-Start Thompson Sampling (DWTS), a practical approach that leverages a Doubly Debiased LASSO (DDL) procedure to identify a sparse set of reliable measured covariates and combines them with key hidden covariates to form a reduced context. By initializing Thompson Sampling (LinTS) priors with DDL-estimated means and variances on these measured features -- while keeping uninformative priors on hidden features -- DWTS effectively harnesses confounded observational data to kick-start adaptive clinical trials. Evaluated on both a purely synthetic environment and a virtual environment created using real cardiovascular risk dataset, DWTS consistently achieves lower cumulative regret than standard LinTS, showing how offline causal insights from observational data can improve trial efficiency and support more personalized treatment decisions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17283 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine Jaiswal, Prateek Keyvanshokooh, Esmaeil Cao, Junyu Machine Learning Optimization and Control Applications Randomized clinical trials often require large patient cohorts before drawing definitive conclusions, yet abundant observational data from parallel studies remains underutilized due to confounding and hidden biases. To bridge this gap, we propose Deconfounded Warm-Start Thompson Sampling (DWTS), a practical approach that leverages a Doubly Debiased LASSO (DDL) procedure to identify a sparse set of reliable measured covariates and combines them with key hidden covariates to form a reduced context. By initializing Thompson Sampling (LinTS) priors with DDL-estimated means and variances on these measured features -- while keeping uninformative priors on hidden features -- DWTS effectively harnesses confounded observational data to kick-start adaptive clinical trials. Evaluated on both a purely synthetic environment and a virtual environment created using real cardiovascular risk dataset, DWTS consistently achieves lower cumulative regret than standard LinTS, showing how offline causal insights from observational data can improve trial efficiency and support more personalized treatment decisions. |
| title | Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine |
| topic | Machine Learning Optimization and Control Applications |
| url | https://arxiv.org/abs/2505.17283 |