Causal machine learning: A survey and open problems
Causal Machine Learning (CausalML) is an umbrella term for machine learning methods
that formalize the data-generation process as a structural causal model (SCM). This …
that formalize the data-generation process as a structural causal model (SCM). This …
Semiparametric proximal causal inference
Skepticism about the assumption of no unmeasured confounding, also known as
exchangeability, is often warranted in making causal inferences from observational data; …
exchangeability, is often warranted in making causal inferences from observational data; …
Provably efficient reinforcement learning in partially observable dynamical systems
Abstract We study Reinforcement Learning for partially observable systems using function
approximation. We propose a new PO-bilinear framework, that is general enough to include …
approximation. We propose a new PO-bilinear framework, that is general enough to include …
Causal inference under unmeasured confounding with negative controls: A minimax learning approach
We study the estimation of causal parameters when not all confounders are observed and
instead negative controls are available. Recent work has shown how these can enable …
instead negative controls are available. Recent work has shown how these can enable …
A minimax learning approach to off-policy evaluation in confounded partially observable markov decision processes
We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes
(POMDPs), where the evaluation policy depends only on observable variables and the …
(POMDPs), where the evaluation policy depends only on observable variables and the …
Causal effect inference for structured treatments
We address the estimation of conditional average treatment effects (CATEs) for structured
treatments (eg, graphs, images, texts). Given a weak condition on the effect, we propose the …
treatments (eg, graphs, images, texts). Given a weak condition on the effect, we propose the …
Proximal causal inference for complex longitudinal studies
A standard assumption for causal inference about the joint effects of time-varying treatment
is that one has measured sufficient covariates to ensure that within covariate strata, subjects …
is that one has measured sufficient covariates to ensure that within covariate strata, subjects …
Pessimism in the face of confounders: Provably efficient offline reinforcement learning in partially observable markov decision processes
We study offline reinforcement learning (RL) in partially observable Markov decision
processes. In particular, we aim to learn an optimal policy from a dataset collected by a …
processes. In particular, we aim to learn an optimal policy from a dataset collected by a …
Long-term causal inference under persistent confounding via data combination
We study the identification and estimation of long-term treatment effects when both
experimental and observational data are available. Since the long-term outcome is …
experimental and observational data are available. Since the long-term outcome is …
Deep proxy causal learning and its application to confounded bandit policy evaluation
Proxy causal learning (PCL) is a method for estimating the causal effect of treatments on
outcomes in the presence of unobserved confounding, using proxies (structured side …
outcomes in the presence of unobserved confounding, using proxies (structured side …