We propose Distribution Embedding Networks (DEN) for classification with...
We consider learning to optimize a classification metric defined by a
bl...
We address the problem of training models with black-box and hard-to-opt...
We consider the problem of improving fairness when one lacks access to a...
Real-world machine learning applications often have complex test metrics...
Markovian processes have long been used to model stochastic environments...
Predictive state representations (PSRs) offer an expressive framework fo...
We address the problem of automatic generation of features for value fun...
Bayesian priors offer a compact yet general means of incorporating domai...