Goto

Collaborating Authors

 frequent discrete update


problem (R1

Neural Information Processing Systems

We thank the reviewers for their thoughtful feedbacks. We are glad all reviewers find the paper to be well-written and clearly positioned w.r.t. We introduce "probabilistic path" ( W e will expand and include the above proof sketch in camera-ready version. This seems a factual misunderstanding. We can't imagine a stronger comparison.