Kernel Treatment Effects with Adaptively Collected Data
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_ | 1866917455653240832 |
|---|---|
| author | Zenati, Houssam Bozkurt, Bariscan Gretton, Arthur |
| author_facet | Zenati, Houssam Bozkurt, Bariscan Gretton, Arthur |
| contents | Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d.\ assumptions that underpin classical asymptotics. At the same time, many questions of interest are distributional, extending beyond average effects. Kernel treatment effects (KTE) provide a flexible framework by representing interventional outcome distributions in an RKHS and comparing them via kernel distances. We present the first kernel-based framework for distributional inference under adaptive data collection. Our method combines doubly robust RKHS scores with a witness function learned on one fold, and performs inference on a second fold using a projected, sequentially normalized scalar statistic with valid type-I error. Experiments show that the resulting procedure is well calibrated and effective for both mean shifts and higher-moment differences, outperforming adaptive baselines limited to scalar effects. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10245 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Kernel Treatment Effects with Adaptively Collected Data Zenati, Houssam Bozkurt, Bariscan Gretton, Arthur Machine Learning Methodology Adaptive experiments improve efficiency by adjusting treatment assignments based on past outcomes, but this adaptivity breaks the i.i.d.\ assumptions that underpin classical asymptotics. At the same time, many questions of interest are distributional, extending beyond average effects. Kernel treatment effects (KTE) provide a flexible framework by representing interventional outcome distributions in an RKHS and comparing them via kernel distances. We present the first kernel-based framework for distributional inference under adaptive data collection. Our method combines doubly robust RKHS scores with a witness function learned on one fold, and performs inference on a second fold using a projected, sequentially normalized scalar statistic with valid type-I error. Experiments show that the resulting procedure is well calibrated and effective for both mean shifts and higher-moment differences, outperforming adaptive baselines limited to scalar effects. |
| title | Kernel Treatment Effects with Adaptively Collected Data |
| topic | Machine Learning Methodology |
| url | https://arxiv.org/abs/2510.10245 |