Results 1  10
of
408
Efficient SVM training using lowrank kernel representations
 Journal of Machine Learning Research
, 2001
"... SVM training is a convex optimization problem which scales with the training set size rather than the feature space dimension. While this is usually considered to be a desired quality, in large scale problems it may cause training to be impractical. The common techniques to handle this difficulty ba ..."
Abstract

Cited by 244 (3 self)
 Add to MetaCart
(Show Context)
SVM training is a convex optimization problem which scales with the training set size rather than the feature space dimension. While this is usually considered to be a desired quality, in large scale problems it may cause training to be impractical. The common techniques to handle this difficulty basically build a solution by solving a sequence of small scale subproblems. Our current effort is concentrated on the rank of the kernel matrix as a source for further enhancement of the training procedure. We first show that for a low rank kernel matrix it is possible to design a better interior point method (IPM) in terms of storage requirements as well as computational complexity. We then suggest an efficient use of a known factorization technique to approximate a given kernel matrix by a low rank matrix, which in turn will be used to feed the optimizer. Finally, we derive an upper bound on the change in the objective function value based on the approximation error and the number of active constraints (support vectors). This bound is general in the sense that it holds regardless of the approximation method.
Sparse Gaussian processes using pseudoinputs
 Advances in Neural Information Processing Systems 18
, 2006
"... We present a new Gaussian process (GP) regression model whose covariance is parameterized by the the locations of M pseudoinput points, which we learn by a gradient based optimization. We take M ≪ N, where N is the number of real data points, and hence obtain a sparse regression method which has O( ..."
Abstract

Cited by 218 (13 self)
 Add to MetaCart
(Show Context)
We present a new Gaussian process (GP) regression model whose covariance is parameterized by the the locations of M pseudoinput points, which we learn by a gradient based optimization. We take M ≪ N, where N is the number of real data points, and hence obtain a sparse regression method which has O(M 2 N) training cost and O(M 2) prediction cost per test case. We also find hyperparameters of the covariance function in the same joint optimization. The method can be viewed as a Bayesian regression model with particular input dependent noise. The method turns out to be closely related to several other sparse GP approaches, and we discuss the relation in detail. We finally demonstrate its performance on some large data sets, and make a direct comparison to other sparse GP methods. We show that our method can match full GP performance with small M, i.e. very sparse solutions, and it significantly outperforms other approaches in this regime. 1
On the Nyström Method for Approximating a Gram Matrix for Improved KernelBased Learning
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2005
"... A problem for many kernelbased methods is that the amount of computation required to find the solution scales as O(n³), where n is the number of training examples. We develop and analyze an algorithm to compute an easilyinterpretable lowrank approximation to an nn Gram matrix G such that compu ..."
Abstract

Cited by 187 (11 self)
 Add to MetaCart
A problem for many kernelbased methods is that the amount of computation required to find the solution scales as O(n³), where n is the number of training examples. We develop and analyze an algorithm to compute an easilyinterpretable lowrank approximation to an nn Gram matrix G such that computations of interest may be performed more rapidly. The approximation is of the form G k = CW , where C is a matrix consisting of a small number c of columns of G and W k is the best rankk approximation to W , the matrix formed by the intersection between those c columns of G and the corresponding c rows of G. An important aspect of the algorithm is the probability distribution used to randomly sample the columns; we will use a judiciouslychosen and datadependent nonuniform probability distribution. Let F denote the spectral norm and the Frobenius norm, respectively, of a matrix, and let G k be the best rankk approximation to G. We prove that by choosing O(k/# ) columns both in expectation and with high probability, for both # = 2, F , and for all k : 0 rank(W ). This approximation can be computed using O(n) additional space and time, after making two passes over the data from external storage. The relationships between this algorithm, other related matrix decompositions, and the Nyström method from integral equation theory are discussed.
Sparse online gaussian processes
 Neural Computation
"... Minor corrections included a a The authors acknowledge reader feedbacks We develop an approach for sparse representations of Gaussian Process (GP) models (which are Bayesian types of kernel machines) in order to overcome their limitations for large data sets. The method is based on a combination of ..."
Abstract

Cited by 178 (8 self)
 Add to MetaCart
(Show Context)
Minor corrections included a a The authors acknowledge reader feedbacks We develop an approach for sparse representations of Gaussian Process (GP) models (which are Bayesian types of kernel machines) in order to overcome their limitations for large data sets. The method is based on a combination of a Bayesian online algorithm together with a sequential construction of a relevant subsample of the data which fully specifies the prediction of the GP model. By using an appealing parametrisation and projection techniques that use the RKHS norm, recursions for the effective parameters and a sparse Gaussian approximation of the posterior process are obtained. This allows both for a propagation of predictions as well as of Bayesian error measures. The significance and robustness of our approach is demonstrated on a variety of experiments. Sparse Online Gaussian Processes 2
Fast Sparse Gaussian Process Methods: The Informative Vector Machine
 Advances in Neural Information Processing Systems 15
, 2003
"... We present a framework for sparse Gaussian process (GP) methods which uses forward selection with criteria based on informationtheoretic principles, previously suggested for active learning. Our goal is not only to learn dsparse predictors (which can be evaluated in O(d) rather than O(n), d ..."
Abstract

Cited by 173 (30 self)
 Add to MetaCart
(Show Context)
We present a framework for sparse Gaussian process (GP) methods which uses forward selection with criteria based on informationtheoretic principles, previously suggested for active learning. Our goal is not only to learn dsparse predictors (which can be evaluated in O(d) rather than O(n), d n, n the number of training points), but also to perform training under strong restrictions on time and memory requirements. The scaling of our method is at most O(n ), and in large realworld classification experiments we show that it can match prediction performance of the popular support vector machine (SVM), yet can be significantly faster in training. In contrast to the SVM, our approximation produces estimates of predictive probabilities (`error bars'), allows for Bayesian model selection and is less complex in implementation.
Incremental Online Learning in High Dimensions
 Neural Computation
, 2005
"... Locally weighted projection regression (LWPR) is a new algorithm for incremental nonlinear function approximation in high dimensional spaces with redundant and irrelevant input dimensions. At its core, it employs nonparametric regression with locally linear models. In order to stay computationally e ..."
Abstract

Cited by 162 (18 self)
 Add to MetaCart
Locally weighted projection regression (LWPR) is a new algorithm for incremental nonlinear function approximation in high dimensional spaces with redundant and irrelevant input dimensions. At its core, it employs nonparametric regression with locally linear models. In order to stay computationally e#cient and numerically robust, each local model performs the regression analysis with a small number of univariate regressions in selected directions in input space in the spirit of partial least squares regression. We discuss when and how local learning techniques can successfully work in high dimensional spaces and review the various techniques for local dimensionality reduction before finally deriving the LWPR algorithm. The properties of LWPR are that it i) learns rapidly with second order learning methods based on incremental training, ii) uses statistically sound stochastic leaveoneout cross validation for learning without the need to memorize training data, iii) adjusts its weighting kernels based only on local information in order to minimize the danger of negative interference of incremental learning, iv) has a computational complexity that is linear in the number of inputs, and v) can deal with a large number of  possibly redundant  inputs, as shown in various empirical evaluations with up to 90 dimensional data sets. For a probabilistic interpretation, predictive variance and confidence intervals are derived. To our knowledge, LWPR is the first truly incremental spatially localized learning method that can successfully and e#ciently operate in very high dimensional spaces.
RSVM: Reduced support vector machines
 Data Mining Institute, Computer Sciences Department, University of Wisconsin
, 2001
"... Abstract An algorithm is proposed which generates a nonlinear kernelbased separating surface that requires as little as 1 % of a large dataset for its explicit evaluation. To generate this nonlinear surface, the entire dataset is used as a constraint in an optimization problem with very few variabl ..."
Abstract

Cited by 160 (19 self)
 Add to MetaCart
(Show Context)
Abstract An algorithm is proposed which generates a nonlinear kernelbased separating surface that requires as little as 1 % of a large dataset for its explicit evaluation. To generate this nonlinear surface, the entire dataset is used as a constraint in an optimization problem with very few variables corresponding to the 1%
A unifying view of sparse approximate Gaussian process regression
 Journal of Machine Learning Research
, 2005
"... We provide a new unifying view, including all existing proper probabilistic sparse approximations for Gaussian process regression. Our approach relies on expressing the effective prior which the methods are using. This allows new insights to be gained, and highlights the relationship between existin ..."
Abstract

Cited by 155 (6 self)
 Add to MetaCart
We provide a new unifying view, including all existing proper probabilistic sparse approximations for Gaussian process regression. Our approach relies on expressing the effective prior which the methods are using. This allows new insights to be gained, and highlights the relationship between existing methods. It also allows for a clear theoretically justified ranking of the closeness of the known approximations to the corresponding full GPs. Finally we point directly to designs of new better sparse approximations, combining the best of the existing strategies, within attractive computational constraints.
Diffusion Wavelets
, 2004
"... We present a multiresolution construction for efficiently computing, compressing and applying large powers of operators that have high powers with low numerical rank. This allows the fast computation of functions of the operator, notably the associated Green’s function, in compressed form, and their ..."
Abstract

Cited by 149 (18 self)
 Add to MetaCart
We present a multiresolution construction for efficiently computing, compressing and applying large powers of operators that have high powers with low numerical rank. This allows the fast computation of functions of the operator, notably the associated Green’s function, in compressed form, and their fast application. Classes of operators satisfying these conditions include diffusionlike operators, in any dimension, on manifolds, graphs, and in nonhomogeneous media. In this case our construction can be viewed as a farreaching generalization of Fast Multipole Methods, achieved through a different point of view, and of the nonstandard wavelet representation of CalderónZygmund and pseudodifferential operators, achieved through a different multiresolution analysis adapted to the operator. We show how the dyadic powers of an operator can be used to induce a multiresolution analysis, as in classical LittlewoodPaley and wavelet theory, and we show how to construct, with fast and stable algorithms, scaling function and wavelet bases associated to this multiresolution analysis, and the corresponding downsampling operators, and use them to compress the corresponding powers of the operator. This allows to extend multiscale signal processing to general spaces (such as manifolds and graphs) in a very natural way, with corresponding fast algorithms.
The Kernel Recursive Least Squares Algorithm
 IEEE Transactions on Signal Processing
, 2003
"... We present a nonlinear kernelbased version of the Recursive Least Squares (RLS) algorithm. Our KernelRLS (KRLS) algorithm performs linear regression in the feature space induced by a Mercer kernel, and can therefore be used to recursively construct the minimum mean squared error regressor. Spars ..."
Abstract

Cited by 138 (2 self)
 Add to MetaCart
(Show Context)
We present a nonlinear kernelbased version of the Recursive Least Squares (RLS) algorithm. Our KernelRLS (KRLS) algorithm performs linear regression in the feature space induced by a Mercer kernel, and can therefore be used to recursively construct the minimum mean squared error regressor. Sparsity of the solution is achieved by a sequential sparsification process that admits into the kernel representation a new input sample only if its feature space image cannot be suffciently well approximated by combining the images of previously admitted samples. This sparsification procedure is crucial to the operation of KRLS, as it allows it to operate online, and by effectively regularizing its solutions. A theoretical analysis of the sparsification method reveals its close affinity to kernel PCA, and a datadependent loss bound is presented, quantifying the generalization performance of the KRLS algorithm. We demonstrate the performance and scaling properties of KRLS and compare it to a stateof theart Support Vector Regression algorithm, using both synthetic and real data. We additionally test KRLS on two signal processing problems in which the use of traditional leastsquares methods is commonplace: Time series prediction and channel equalization.