The next point in the iteration process is defined as the minimizer of this model.

As a result we can learn a kernel that transfers to new tasks; we call this Deep Kernel Transfer (DKT) .

The proposed methodology is a variant of principal component regression (PCR).

"NIPS 2013 Neural Information Processing Systems December 5 - 10, Lake Tahoe, Nevada, USA",,, "Paper ID:","1011" "Title:","Distributed k-means and k-median clustering on general communication topologies" Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper provides provably efficient algorithms for performing k-means and k-median clustering in the distributed setting. The main focus of the paper is minimizing communication cost in the distributed network. Although, i am not very much aware of the literature, the paper seems to provide a very novel idea of distributed coresets that leads to clustering algorithms which provably improves the state of the art communication complexity significantly. Existing approaches only use the idea of approximating coresets by taking the union of local coresets.

While several papers have investigated computationally and statistically efficient methods for learning Gaussian mixtures, precise minimax bounds for their statistical performance as well as fundamental limits in high-dimensional settings are not well-understood. In this paper, we provide precise information theoretic bounds on the clustering accuracy and sample complexity of learning a mixture of two isotropic Gaussians in high dimensions under small mean separation. If there is a sparse subset of relevant dimensions that determine the mean separation, then the sample complexity only depends on the number of relevant dimensions and mean separation, and can be achieved by a simple computationally efficient procedure. Our results provide the first step of a theoretical basis for recent methods that combine feature selection and clustering.

In this paper, we theoretically study the problem of binary c lassification in the presence of random classification noise -- the learner, inste ad of seeing the true labels, sees labels that have independently been flipped with s ome small probability. Moreover, random label noise is class-conditional -- the flip probability depends on the class. W e provide two approaches to suitably modify an y given surrogate loss function. First, we provide a simple unbiased estimato r of any loss, and obtain performance bounds for empirical risk minimization in the presence of iid data with noisy labels. If the loss function satisfies a simpl e symmetry condition, we show that the method leads to an efficient algorithm for emp irical minimization. Second, by leveraging a reduction of risk minimizatio n under noisy labels to classification with weighted 0-1 loss, we suggest the use o f a simple weighted surrogate loss, for which we are able to obtain strong empiri cal risk bounds. This approach has a very remarkable consequence -- methods used in practice such as biased SVM and weighted logistic regression are provably noise-tolerant. On a synthetic non-separable dataset, our methods achieve ove r 88% accuracy even when 40% of the labels are corrupted, and are competitive wit h respect to recently proposed methods for dealing with label noise in several ben chmark datasets.