Structured Counterfactual Inference
Can we get better trade-offs by incorporating more structure into counterfactual learning algorithms?
In batch learning from bandit feedback, we observe a context (e.g., some covariates describing a patient or a customer), choose an action (e.g., a treatment or a recommendation) and observe an outcome (e.g., treatment effect or a proxy for user experience). However, we may only observe the effects of a logging policy, that we hope to improve over. Dealing with biases and variance for offline policy learning is a challenging setting.
We study two specific scenarios of policy optimization in which additional structure (e.g., monotonicity or reward sparsity) can be exploited to provide better bias-variance trade-offs.
Romain Lopez
Postdoctoral Scholar
My research interests lie at the intersection of statistics, computation and modeling. A significant part of my research is driven by building more statistically accurate and faster machine learning software for analyzing biological data, with a focus on single-cell transcriptomics.