Counterfactual Density Estimation using Kernel Stein Discrepancies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909111259496448 |
|---|---|
| author | Martinez-Taboada, Diego Kennedy, Edward H. |
| author_facet | Martinez-Taboada, Diego Kennedy, Edward H. |
| contents | Causal effects are usually studied in terms of the means of counterfactual distributions, which may be insufficient in many scenarios. Given a class of densities known up to normalizing constants, we propose to model counterfactual distributions by minimizing kernel Stein discrepancies in a doubly robust manner. This enables the estimation of counterfactuals over large classes of distributions while exploiting the desired double robustness. We present a theoretical analysis of the proposed estimator, providing sufficient conditions for consistency and asymptotic normality, as well as an examination of its empirical performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_16129 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Counterfactual Density Estimation using Kernel Stein Discrepancies Martinez-Taboada, Diego Kennedy, Edward H. Methodology Causal effects are usually studied in terms of the means of counterfactual distributions, which may be insufficient in many scenarios. Given a class of densities known up to normalizing constants, we propose to model counterfactual distributions by minimizing kernel Stein discrepancies in a doubly robust manner. This enables the estimation of counterfactuals over large classes of distributions while exploiting the desired double robustness. We present a theoretical analysis of the proposed estimator, providing sufficient conditions for consistency and asymptotic normality, as well as an examination of its empirical performance. |
| title | Counterfactual Density Estimation using Kernel Stein Discrepancies |
| topic | Methodology |
| url | https://arxiv.org/abs/2309.16129 |