However, such a distillation process can yield a highly suboptimal programmatic policy -- i.e., a large

Neural Information Processing Systems http://nips.cc/

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors reduce online learning problems (linear regret/bandit, online convex optimization, boosting) into another framework known as drifting games. It is quite related to a similar idea of Rakhlin, Shamir & Sridharan and can be seen as the decrease of some potential mappings (as it is really usual know, see the textbook of Cesa-Bianchi & Lugosi). Those reductions give another interpretation to famous online algorithms (exponential weights, squared potential, etc) and allow to recover their guarantees with new proofs. This is interesting from a theoretical point of view, but I do not see the impact it could have.

Applying probabilistic models to reinforcement learning (RL) enables the uses of powerful optimisation tools such as variational inference in RL.

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation.

In this paper, we consider online learning in generalized linear contextual bandits where rewards are not immediately observed.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper describes a Bayesian model for online learning in the context of random forests models for supervised classification. The main contribution of the paper is the formulation of a novel prior on binary rooted trees that relies on the Mondrian process. An additional novelty of the paper is the use of hierarchical normalized stable processes as priors for the probabilities of the different classes at each terminal node. The paper is well written and the formulation novel.

Given an input passage and an answer, the task is to generate a question that asks for the answer.

The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher).