First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors study a variant of ratio cut with R clusters where the balancing function is biased towards partitions where each cluster has the same size. The main contribution of the paper is a continuous formulation and an algorithm to optimize the criterion directly, whereas previous algorithms are mostly limited to recursive splitting. The direct solution of multi-cut problems instead of using recursive splitting is an important problem given the new developments in finding balanced graph cuts [3,4,5,11,12,18]. The authors first describe the discrete problem (P) and then derive a relaxation of the problem (P-rlx).

O, is a hybridization of these approaches that regularizes a model for explanation quality at training time.

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

In this paper, we propose an active algorithm to find the graph with high probability and analyze its query complexity.

TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper proposes a variational bound on the length scale parameters of square-exponential-kernel Gaussian process regression models. The main idea is to separate the function to be inferred into a standardised sample from a unit-length-scale square-exponential kernel, and a linear scaling map of that latent function, then to impose factorisation between these two objects via a variational bound. The paper is well written. It uses clear language and provides a compact introduction to previous work.

Q2: Please summarize your review in 1-2 sentences The paper's main contribution are theoretical error bounds for a recently proposed low-rank tensor decomposition approach. The paper seems technically sound, but the results are somewhat incremental and may suffer from limited impact at NIPS.

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

We consider the problem of estimating a vector from its noisy measurements using a prior specified only through a denoising function. Recent work on plug-and-play priors (PnP) and regularization-by-denoising (RED) has shown the state-of-the-art performance of estimators under such priors in a range of imaging tasks.