Model selection is an important problem of cost-sensitive SVM (CS-SVM). Although using solution path to find global optimal parameters is a powerful method for model selection, it is a challenge to extend the framework to solve two regularization parameters of CS-SVM simultaneously. To overcome this challenge, we make three main steps in this paper. (i) A critical-regions-based bi-parameter space partition algorithm is proposed to present all piecewise linearities of CS-SVM. (ii) An invariant-regions-based bi-parameter space partition algorithm is further proposed to compute empirical errors for all parameter pairs. (iii) The global optimal solutions for K-fold cross validation are computed by superposing K invariant region based bi-parameter space partitions into one. The three steps constitute the model selection of CS-SVM which can find global optimal parameter pairs in K-fold cross validation. Experimental results on seven normal datsets and four imbalanced datasets, show that our proposed method has better generalization ability and than various kinds of grid search methods, however, with less running time.

Feature selection measures are often explained by the analogy to a rule to measure the “distance” of sets of features to the “closest” ideal sets of features. An ideal feature set is such that it can determine classes uniquely and correctly. This way of explanation was just an analogy before this paper. In this paper, we show a way to map arbitrary feature sets of datasets into a common metric space, which is indexed by a real number p with 1 ≤ p ≤ ∞. Since this determines the distance between an arbitrary pair of feature sets, even if they belong to different datasets, the distance of a feature set to the closest ideal feature set can be used as a feature selection measure. Surprisingly, when p = 1, the measure is identical to the Bayesian risk, which is probably the feature selection measure that is used the most widely in the literature. For 1 < p ≤ ∞, the measure is novel and has significantly different properties from the Bayesian risk. We also investigate the correlation between measurements by these measures and classification accuracy through experiments. As a result, we show that our novel measures with p > 1 exhibit stronger correlation than the Bayesian risk.

Multi-view outlier detection is a challenging problem due to the inconsistent behaviors and complicated distributions of samples across different views. The existing approaches are designed to identify the outlier exhibiting inconsistent characteristics across different views. However, due to the inevitable system errors caused by data-captured sensors or others, there always exists another type of outlier, which consistently behaves abnormally in individual view. Unfortunately, this kind of outlier is neglected by all the existing multi-view outlier detection methods, consequently their outlier detection performances are dramatically harmed.In this paper, we propose a novel Dual-regularized Multi-view Outlier Detection method (DMOD) to detect both kinds of anomalies simultaneously. By representing the multi-view data with latent coefficients and sample-specific errors, we characterize each kind of outlier explicitly. Moreover, an outlier measurement criterion is well-designed to quantify the inconsistency. To solve the proposed non-smooth model, a novel optimization algorithm is proposed in an iterative manner. We evaluate our method on five datasets with different outlier settings. The consistent superior results to other state-of-the-art methods demonstrate the effectiveness of our approach.

It is also useful for scientific discovery like in neuroscience, like correlation of X, Y only test for (univariate) to see if a stimulus X (say an image) is independent linear independence, natural alternatives like of the brain activity Y (say fMRI) in a relevant part of mutual information of X, Y are hard to estimate the brain. Since detecting nonlinear correlations is much easier due to a serious curse of dimensionality. A recent than estimating a nonparametric regression function (of approach, avoiding both issues, estimates norms of Y onto X), it can be done at smaller sample sizes, with further an operator in Reproducing Kernel Hilbert Spaces samples collected for estimation only if an effect is detected (RKHSs). Our main contribution is strong empirical by the hypothesis test. For such situations, correlation evidence that by employing shrunk operators only tests for univariate linear independence, while other when the sample size is small, one can attain an improvement statistics like mutual information that do characterize multivariate in power at low false positive rates. We independence are hard to estimate from data, suffering analyze the effects of Stein shrinkage on a popular from a serious curse of dimensionality. A recent popular test statistic called HSIC (Hilbert-Schmidt Independence approach for this problem (and a related two-sample testing Criterion). Our observations provide insights problem) involve the use of quantities defined in reproducing into two recently proposed shrinkage estimators, kernel Hilbert spaces (RKHSs) - see [Gretton et al., 2006; SCOSE and FCOSE - we prove that SCOSE Harchaoui et al., 2007; Gretton et al., 2005b; 2005a].

My research goal involves simultaneously addressing statistical and computational tradeoffs encountered in modern data analysis and high-dimensional machine learning (eg: hypothesis testing, regression, classification). My future interests include incorporating additional constraints like privacy or communication, and settings involving hidden utilities of multiple cooperative agents or competitive adversaries.

In partial label learning, each training example is associated with a set of candidate labels, among which only one is valid. An intuitive strategy to learn from partial label examples is to treat all candidate labels equally and make prediction by averaging their modeling outputs. Nonetheless, this strategy may suffer from the problem that the modeling output from the valid label is overwhelmed by those from the false positive labels. In this paper, an instance-based approach named IPAL is proposed by directly disambiguating the candidate label set. Briefly, IPAL tries to identify the valid label of each partial label example via an iterative label propagation procedure, and then classifies the unseen instance based on minimum error reconstruction from its nearest neighbors. Extensive experiments show that IPAL compares favorably against the existing instance-based as well as other state-of-the-art partial label learning approaches.

To enjoy more social network services, users nowadays are usually involved in multiple online social media sites at the same time. Across these social networks, users can be connected by both intra-network links (i.e., social links) and inter-network links (i.e., anchor links) simultaneously. In this paper, we want to predict the formation of social links among users in the target network as well as anchor links aligning the target network with other external social networks. The problem is formally defined as the “collective link identification” problem. To solve the collective link identification problem, a unified link prediction framework, CLF (Collective Link Fusion) is proposed in this paper, which consists of two phases: step (1) collective link prediction of anchor and social links, and step (2) propagation of predicted links across the partially aligned “probabilistic networks” with collective random walk. Extensive experiments conducted on two real-world partially aligned networks demonstrate that CLF can perform very well in predicting social and anchor links concurrently.

We study the problem of inducing logic programs in a probabilistic setting, in which both the example descriptions and their classification can be probabilistic. The setting is incorporated in the probabilistic rule learner ProbFOIL+, which combines principles of the rule learner FOIL with ProbLog, a probabilistic Prolog. We illustrate the approach by applying it to the knowledge base of NELL, the Never-Ending Language Learner.

In practical applications, it is often observed that high-dimensional features can yield good performance, while being more costly in both computation and storage. In this paper, we propose a novel method called Bayesian Hashing to learn an optimal Hamming embedding of high-dimensional features, with a focus on the challenging application of face recognition. In particular, a boosted random FERNs classification model is designed to perform efficient face recognition, in which bit correlations are elaborately approximated with a random permutation technique. Without incurring additional storage cost, multiple random permutations are then employed to train a series of classifiers for achieving better discrimination power. In addition, we introduce a sequential forward floating search (SFFS) algorithm to perform model selection, resulting in further performance improvement. Extensive experimental evaluations and comparative studies clearly demonstrate that the proposed Bayesian Hashing approach outperforms other peer methods in both accuracy and speed. We achieve state-of-the-art results on well-known face recognition benchmarks using compact binary codes with significantly reduced computational overload and storage cost.

Building ontologies is a difficult task requiring skills in logics and ontological analysis. Domain experts usually reach as far as organizing a set of concepts into a hierarchy in which the semantics of the relations is under-specified. The categorization of Wikipedia is a huge concept hierarchy of this form, covering a broad range of areas. We propose an automatic method for bootstrapping domain ontologies from the categories of Wikipedia. The method first selects a subset of concepts that are relevant for a given domain. The relevant concepts are subsequently split into classes and individuals, and, finally, the relations between the concepts are classified into subclass_of, instance_of, part_of, and generic related_to. We evaluate our method by generating ontology skeletons for the domains of Computing and Music. The quality of the generated ontologies has been measured against manually built ground truth datasets of several hundred nodes.