First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper presents an algorithm that achieves optimal regret for sellers in posted-price auctions with strategic buyers. The intuition behind the definition of Regret is not clear enough, what does a small regret mean for the seller. There should be more elaboration on the intuition. The paper is well-written with proofs and theorems clearly stated.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors derive a new convex relaxation for the noisy seriation problem (a combinatorial ordering problem, where variables must be ordered on a line such that their pairwise similarities decrease with their distance on this line). Specifically, they use the construction in Goemans [1] based on sorting networks, in order to optimize over the convex set of permutation vectors (ie. the permutahedron) instead of the convex hull of permutation matrices (ie. the Birkhoff polytope). The new representation reduces the number of constraints from Theta(n^2) to Theta(nlog^2n) and turns out to be in practice significantly faster to solve some instances of the seriation problem. I think this paper provides a very appealing convex relaxation to the seriation problem, since it enables to solve much larger instances (up to several thousands with a standard interior point solver, against to a few hundreds with previous relaxation in [2]).

Generative Adversarial Networks (GANs) have shown remarkable results in modeling complex distributions, but their evaluation remains an unsettled issue. Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This manuscript presents a flexible discrete latent-state model for population neural data. Approximations (variational and eq 10,11) are necessary to do inference in powerful flexible model. This is a tool for confirmatory analysis; one major weakness as a explorative tool is the necessity to set up the state hierarchy in advance. Originality: It is a novel approach.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Summary: This paper deals with sampling methods based on linear rate-based neural-networks. First, it shows that symmetric weights (a common constraint in many models) significantly hurt the mixing rate. Then it shows that a (more physiological) non-normal network can have a much faster mixing rate, if the connectivity is optimized for this purpose. This works even if more biological constraints (Dale's law) are imposed.

This problem setting is motivated by the successful deep Q-networks (DQN) framework that falls in this regime.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper introduces the problem of activity shaping, which is a generalization of influence maximization, and allows more elaborate goal functions. The authors use multivariate Hawkes processes as the model, and via a connection to branching processes, they manage to derive a linear connection between the exogenous activity (i.e. the part that can be easily manipulated via incentives) and the overall network activity. This connection can be used in a convex optimization problem, to derive the necessary incentives to reach a global activity pattern in the network. The paper is clearly written, it contains original research, and it is potentially a very significant contribution in the field of influence maximization.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper propose to use CNN to classify rhythms from EEG recordings. A dataset with 13 subjects is analyzed. Temporal and spatiotemporal (STFT) data representation are investigated. The paper is well written with a good review of the relevant literature.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. First, apologies for the brevity of this review-I had written a version with more detailed comments and had found a few typos, but can't find it now. This paper is an application of DNNs to a novel area (finding mathematical identities) and my feeling is that while the ideas are novel, this seems like preliminary work that maybe doesn't quite rise to the level of a NIPS publication. Specifically, your method doesn't seem to show particularly impressive performance in discovering identities, even though you only gave it a very limited set of inputs. The expressions that you were finding identities on were from such a limited set that it would probably have been easier to just work out some mathematical rule to discover them rather than applying DNNs; it seems like using a sledgehammer to crack a nut.