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

While there has been rapid progress in understanding the learning dynamics of neural networks, most such work focuses on the networks' ability to fit input-output relationships. However, many machine learning problems require learning representations with general utility.

After that, we design a two-stage aggregate-and-distribute architecture to explore group-wise semantic interactions and produce the co-saliency features.

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1466" "Title:","Multitask learning meets tensor factorization: task imputation via convex optimization" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. In this paper, the authors study the problem of learning a tensor for the purpose of linear multi-task learning. The authors propose a new weighted version of a previously proposed tensor norm (called latent trace norm) and show that the introduced rescaling yields better bounds on the excess risk as well as improved recovery performance on some datasets. The paper is well written and organized, and the proposed rescaling can potentially have a significant impact in practice, although a more extensive experimental evaluation would have been desirable. The technical results seem to be appropriate and correctly proven.

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 paper proposes a new penalty term that can be used in learning a regression model; it's based on the idea that features are grouped into (possibly overlapping) groups and the penalty term discourages the use of nonzero weights for several features from the same group. The paper describes how to solve the resulting optimization problem and presents an evaluation on several synthetic and realistic datasets, demonstrating that the proposed approach works better than several alternatives. The paper is clearly written and well organized, and seems to present an interesting incremental improvement on various earlier LASSO methods (which are mentioned in the related work section). Comments for the authors: exclusive group LASSO [caption of Figure 1] -- should be Exclusive Eq.(2) [caption of Figure 1] -- space missing; there are several similar occurrences elsewhere G_g \in P({1, 2, ..., p}) denotes a set of group g [page 2] -- I found this sentence unclear.

Group LASSO is widely used to enforce the structural sparsity, which achieves the sparsity at the inter-group level. In this paper, we propose a new formulation called "exclusive group LASSO", which brings out sparsity at intra-group level in the context of feature selection. The proposed exclusive group LASSO is applicable on any feature structures, regardless of their overlapping or non-overlapping structures. We provide analysis on the properties of exclusive group LASSO, and propose an effective iteratively re-weighted algorithm to solve the corresponding optimization problem with rigorous convergence analysis. We show applications of exclusive group LASSO for uncorrelated feature selection. Extensive experiments on both synthetic and real-world datasets validate the proposed method.

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

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 consider logistic regression when the data are contaminated with outliers. No assumptions are made on the outliers, they need not even follow any distribution, which can happen for example when a video is corrupted by sensor errors. The authors provide an innovative algorithm, RoLR, and provide performance guarantees. The algorithm is simple to describe but uses sophisticated ideas, and the mathematics behind the performance guarantees is impressive.