Statistical learning theory

By Vladimir Naumovich Vapnik. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

Citations in the corpus

Meta-Learning for Semi-Supervised Few-Shot Classification (2018, background): “Our algorithm is also related to transductive learning (Vapnik, 1998; Joachims, 1999; Fu et al., 2015), where the base classifier gets refined by seeing the unlabeled examples.”
Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data (2016, background): “farther away from the true relationship as compared to models of M3. It is the trade-off between reducing bias and variance that is at the heart of a number of machine learning algorithms [39], [40], [41]. In scientiﬁc applications,there is another source of information that can be used to ensure th”
Deep Weighted Averaging Classifiers (2018, background): “There is, of course, a long history in machine learning of making predictions directly in terms of training instances, including nearest neighbor methods [9], kernel methods, including support vector machines [5, 8], and transductive learners more broadly [52].”
Learning customized and optimized lists of rules with mathematical programming (2018, methodology): “Algorithms we compare with include boosted decision trees—AdaBoost [22], logistic regression—LR, support vector machines with RBF kernels—SVM [67], random forests—RF [10], CART, and C5.”
Hilbert Space Embeddings and Metrics on Probability Measures (2009, background): “On the other hand, if a kernel is strictly pd, then it need not be universal, which follows from the results due to Dahmen and Micchelli (1987) and Pinkus (2004) for Taylor kernels (Steinwart and Christmann, 2008, Lemma 4.8, Corollary 4.57).”
Domain Adaptation: Learning Bounds and Algorithms (2009, methodology): “This family of algorithms includes support vector machines (SVM) (Cortes & Vapnik, 1995), support vector regression (SVR) (Vapnik, 1998), kernel ridge regression (Saunders et al., 1998), and other algorithms such as those based on the relative entropy regularization (Bousquet & Elisseeff, 2002).”
Optimal Rates for the Regularized Least-Squares Algorithm (2007, background): “We now introduce some basic concepts of statistical learning theory in the regression setting for vector-valued outputs (for details, see [32], [15], [24], [6], [20], and references therein).”
Revisiting Classifier Two-Sample Tests (2016, methodology): “ining data (leading to smaller test sizes). Formally, the relationship between the test accuracy, sample size, and the ﬂexibility of a classiﬁer depends on capacity measures such as the VC-Dimension (Vapnik, 1998). Note that there is no restriction to perform model selection (such as cross-validatio”
Learning from Scarce Experience (2002, background): “Metric entropy is a more refined measure of capacity than VC dimension; the VC dimension is an upper bound on the growth function which is an upper bound on the metric entropy ( Vapnik, 1998 ).”
Kernel Methods for Relation Extraction (2002, methodology): “Kernel methods (Vapnik, 1998, Cristianini and Shawe-Taylor, 2000) are an attractive alternative to feature-based methods.”
Compressed sensing, sparsity, and dimensionality in neuronal information processing and data analysis. (2012, background): “Indeed, several powerful learning algorithms, including support vector machines (SVMs) (see Burges 1998, Vapnik 1998, Smola 2000 for reviews), exploit this form of sparsity to achieve good generalization from relatively few high-dimensional examples.”
Survey of multifidelity methods in uncertainty propagation, inference, and optimization (2018, background): “ for the hyper-parameters have been developed [141, 185, 112, 138, 174, 72]. In particular, kriging models are equipped with error indicators, see, e.g., [185]. There are also support vector machines [207, 49, 23, 188], which have been developed by the machine-learning community for classication tas”
Object perception as Bayesian inference. (2004, methodology): “Neural networks and machine learning models select rules to minimize R emp ( (cid:11) ) (Vapnik 1998,Evgeniou et al 2000,Sch(cid:127)olkopf & Smola 2002).”
Statistical Pattern Recognition: A Review (2000, methodology): “For example, the maximum margin objective was introduced in the context of support vector machines [23] based on structural risk minimization theory [162].”