First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper present a heuristic for node selection in Branch and Bound for Mixed Integer Programs based on machine learning. Although machine learning used for node selection is not new the paper present a new approach (to the best of my knowledge). They utilize a classifier together with an oracle for training two aspects: a node selection policy and a node pruning policy. The first one is used to enforce a linear order/priority on the current open nodes of the Branch and Bound while the second one is used to further shrink the list of open nodes by pruning the unpromising ones.

Specifically, label propagation is adopted to instantiate the labeling confidence of partial label examples.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The manuscript describes a very interesting model for the analysis of brain states for multi-region LFP time-series. The time-series are separated in different time-windows. An infinite mixture of Gaussian Processes is considered to model the observations in each window. Brain states are assigned to each observation by means of an underlying HDP and brain regions are assigned to clusters by means of a HDP.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Authors propose a method of estimating a graphical model for continuous data that blends the following three, established ideas: 1) assume the data follows a multivariate Gaussian and estimate using the graphical lasso; 2) do not assume the data follows a multivariate Gaussian and instead use a Gaussian copula, the nonparanormal, to allow arbitrary single variable marginals; or 3) assume a specific tree-structured factorization and model arbitrary bivariate marginals along the tree structure. The proposed method introduces the blossom tree, which is a specific factorization of the model into a collection of densely connected blossom components that are connected by a specific set of tree edges. In particular, each blossom is connected (via a pedicel node) to at most one tree edge. The blossom components are modeled as sparse multivariate Gaussians (or using the non-paranormal copula) and the tree edges are modeled as arbitrary bivariate distributions with single variable marginals that are consistent with the marginal of any blossom pedicel to which they are attached.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper presents a novel approach for column sampling when the data point clusters comprise of non-convex hulls. Column sampling is important in selecting a small subset of data that represents the properties of the original dataset. The presented approach is based upon the computation of Zeta hulls. The authors model the graph cycles by means of the sum-product rule and integrate them using the Zeta function. The authors set up the optimization problem as finding the subset of points with the strongest point extremenesses.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper combines evidence-based clustering with an importance sampling approach. It further optimizes the weight function calculation of importance sampling, by using a second sampler to estimate the number of true groundings. I recommend to accept this paper because of the importance of the evidence problem, and the fact that the proposed solution is very general and scalable. The paper is well-written and clear, except for Figure 1 (b) and Equations 5,6, and 7, which are poorly explained.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. An attentional mechanism is added to a feedforward convolutional network, with recurrence introduced by the feedback of succeeding attentional focus locations. The system is trained using RL, due to issues of differentiability making the performance gradient unavailable. The system achieves competitive performance, with a dramatic reduction in computational burden. This work tackles an important problem, and makes good progress.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper considers weighted majority algorithm and establishes consistency (error rate of the aggregator tending to zero) results under two settings: (1) when the competence level (risk of each expert) is known in advance and (2) when it is estimated. For case (2), frequentist and Bayesian methods for estimating the competence level are provided. For case (1), consistency is established in terms of providing upper and lower bounds on the error rate of the aggregator, which involve standard calculations ( apart from the fact that upper bound is established by invoking a result by Kearns and Saul, instead of Hoeffding's inequality). For case (2) under the frequentist setting, an independent set of labeled inputs is used to estimate the competence level of each expert.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Paper ID: 39 Title: Robust Classification Under Sample Selection Bias NOTE: Due to the short reviewing time and out of fairness to the other papers I was reviewing, I DID NOT do more than glance over the supplementary material. In most cases, I therefore did not verify that results claimed by the authors are correct, but instead checked that they are plausible. Summary: This paper is about how to adjust a classifier when the training set is not representative of the test set; a canonical example is active learning, but the problem can also appear in recalibration. The goal is to find an effective method in the finite-sample regime, since most results are asymptotics.