Abstract | ||
---|---|---|
We address the problem of causal effect estimation in the presence of unobserved confounding, but where proxies for the latent confounder(s) are observed. We propose two kernel-based methods for nonlinear causal effect estimation in this setting: (a) a two-stage regression approach, and (b) a maximum moment restriction approach. We focus on the proximal causal learning setting, but our methods can be used to solve a wider class of inverse problems characterised by a Fredholm integral equation. In particular, we provide a unifying view of two-stage and moment restriction approaches for solving this problem in a nonlinear setting. We provide consistency guarantees for each algorithm, and demonstrate that these approaches achieve competitive results on synthetic data and data simulating a real-world task. In particular, our approach outperforms earlier methods that are not suited to leveraging proxy variables. |
Year | Venue | DocType |
---|---|---|
2021 | INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139 | Conference |
Volume | ISSN | Citations |
139 | 2640-3498 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Afsaneh Mastouri | 1 | 0 | 0.34 |
Yuchen Zhu | 2 | 0 | 0.34 |
Limor Gultchin | 3 | 0 | 1.35 |
Anna Korba | 4 | 3 | 3.42 |
Ricardo Bezerra de Andrade e Silva | 5 | 109 | 24.56 |
Matt J. Kusner | 6 | 279 | 18.55 |
Arthur Gretton | 7 | 3638 | 226.18 |
Krikamol Muandet | 8 | 211 | 17.10 |