Response for " Information Theoretic Counterfactual Learning from MNAR Feedback "

We thank the reviewers for their time and for their valuable advice to our work. We thank the reviewer for advice to perform evaluation using other metrics used in the literature. We will include these results in the final version of this paper. Liang et al. (2015) considered recommendation from positive feedback alone (implicit data); however, we consider We postulate that the CVIB's weakness in MSE lies in the absence of We believe that randomness in experiments does exist. On the other, Fig.3 in paper shows the 10 runs of MF-CVIB where it Please refer to the response to Reviewer #1 .