Asia
AsymptoticallyExactErrorCharacterizationof OfflinePolicyEvaluationwithMisspecifiedLinear Models
Recently, theoretical understanding of OPE has been rapidly advanced under (approximate) realizability assumptions, i.e., where the environments of interest are well approximated with the given hypothetical models.
Exact inference in structured prediction
Neural Information Processing Systems http://nips.cc/
Precision-Recall Balanced Topic Modelling
Neural Information Processing Systems http://nips.cc/
On the Computational Complexity of Private High-dimensional Model Selection
In this paper, we consider the problem of private model selection in high-dimensional sparse regression which has been one of the central topics in statistical research over the past decade.
Meta-InverseReinforcementLearningwith ProbabilisticContextVariables
Tothis end,wepropose adeep latent variable model thatiscapable oflearning rewards from demonstrations of distinct but related tasks in an unsupervised way.
