This paper concerns the control of text-guided generative models, where ...
We introduce the Conditional Independence Regression CovariancE (CIRCE),...
Consider the problem of estimating the causal effect of some attribute o...
Machine learning methods can be unreliable when deployed in domains that...
Real-world classification problems must contend with domain shift, the
(...
We address the problem of using observational data to estimate peer cont...
A fundamental goal of scientific research is to learn about causal
relat...
Informally, a `spurious correlation' is the dependence of a model on som...
The defining challenge for causal inference from observational data is t...
ML models often exhibit unexpectedly poor behavior when they are deploye...
We consider the problem of estimating the causal effects of linguistic
p...
Instrumental variable methods provide a powerful approach to estimating
...
It is a truth universally acknowledged that an observed association with...
This paper addresses the use of neural networks for the estimation of
tr...
We address causal inference with text documents. For example, does addin...
We consider causal inference in the presence of unobserved confounding. ...
We consider the problem of feature selection using black box predictive
...
Empirical risk minimization is the principal tool for prediction problem...
Modern neural networks are highly overparameterized, with capacity to
su...
A variety of machine learning tasks---e.g., matrix factorization, topic
...
Sparse exchangeable graphs resolve some pathologies in traditional rando...