Jaz Kandola

Abstract (2008)

Koby Crammer, Jaz Kandola, Yoram Singer

Online algorithms for classification often require vast amounts of memory and computation time when employed in conjunction with kernel functions. In this paper we describe and analyze a simple...

1 Graph Kernels by Spectral Transforms (2008)

Xiaojin Zhu, Jaz Kandola, John Lafferty, Zoubin Ghahramani

Many graph-based semi-supervised learning methods can be viewed as imposing smoothness conditions on the target function with respect to a graph representing the data points to be labeled. The...

Abstract (2008)

Koby Crammer, Jaz Kandola, Yoram Singer

Online algorithms for classification often require vast amounts of memory and computation time when employed in conjunction with kernel functions. In this paper we describe and analyze a simple...

On the Concentration of Spectral Properties (2007)

John Shawe-Taylor, Nello Cristianini, Jaz Kandola

We consider the problem of measuring the eigenvalues of a randomly drawn sample of points. We show that these values can be reliably estimated as can the sum of the tail of eigenvalues. Furthermore,...

Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning (2005)

Zhu, Xiaojin, Kandola, Jaz, Ghahramani, Zoubin, Lafferty, John

We present an algorithm based on convex optimization for constructing kernels for semi-supervised learning. The kernel matrices are derived from the spectral decomposition of graph Laplacians, and...

Graph Kernels by Spectral Transforms (2005)

Zhu, Xiaojin, Kandola, Jaz, Lafferty, John, Ghahramani, Zoubin

Many graph-based semi-supervised learning methods can be viewed as imposing smoothness conditions on the target function with respect to a graph representing the data points to be labeled. The...

On the Eigenspectrum of the Gram Matrix and the Generalisation Error of Kernel PCA (2005)

John Shawe-taylor, Nello Cristianini, Jaz Kandola

Abstract — In this paper the relationships between the eigenvalues of the m × m Gram matrix K for a kernel κ(·, ·) corresponding to a sample x1,..., xm drawn from a density p(x) and the...

Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning (2005)

Xiaojin Zhu, Jaz Kandola, Zoubin Ghahramani, John Lafferty

We present an algorithm based on convex optimization for constructing kernels for semi-supervised learning. The kernel matrices are derived from the spectral decomposition of graph Laplacians, and...

Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning (2005)

Xiaojin Zhu, Jaz Kandola, Zoubin Ghahramani, John Lafferty

We present an algorithm based on convex optimization for constructing kernels for semi-supervised learning. The kernel matrices are derived from the spectral decomposition of graph Laplacians, and...

On the Eigenspectrum of the Gram matrix and the generalisation error of kernel PCA (2004)

Shawe-Taylor, John, Williams, Chris, Cristianini, Nello, Kandola, Jaz

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel k(.,.) corresponding to a sample x1,...,xm drawn from a density p(x) and the eigenvalues of...

On the Eigenspectrum of the Gram matrix and the generalisation error of kernel PCA (2004)

Shawe-Taylor, John, Williams, Chris, Cristianini, Nello, Kandola, Jaz

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel k(.,.) corresponding to a sample x1,...,xm drawn from a density p(x) and the eigenvalues of...

On the Eigenspectrum of the Gram Matrix and the Generalisation Error of Kernel PCA (2004)

Shawe-Taylor, John, Williams, Christopher, Cristianini, Nello, Kandola, Jaz

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel ·(.;.) corresponding to a sample x1,...,xm drawn from a density p(x) and the eigenvalues of...

On the Eigenspectrum of the Gram matrix and the generalisation error of kernel PCA (2004)

Shawe-Taylor, John, Williams, Chris, Cristianini, Nello, Kandola, Jaz

In this paper we analyze the relationships between the eigenvalues of the m x m Gram matrix K for a kernel k(.,.) corresponding to a sample x1,...,xm drawn from a density p(x) and the eigenvalues of...

Sources of Success for Boosted Wrapper Induction (2004)

David Kauchak, Joseph Smarr, Charles Elkan, Jaz Kandola

In this paper, we examine an important recent rule-based information extraction (IE) technique named Boosted Wrapper Induction (BWI) by conducting experiments on a wider variety of tasks than...

Online Classification on a Budget (2003)

Koby Crammer, Jaz Kandola, Royal Holloway, Yoram Singer

Online algorithms for classification often require vast amounts of memory and computation time when employed in conjunction with kernel functions. In this paper we describe and analyze a simple...

Learning semantic similarity (2002)

Jaz Kandola, John Shawe-taylor, Nello Cristianini

The standard representation of text documents as bags of words suers from well known limitations, mostly due to its inability to exploit semantic similarity between terms. Attempts to incorporate...

On kernel-target alignment (2002)

Nello Cristianini, Jaz Kandola, Andre Elisseeff, John Shawe-Taylor

Editor: Kernel based methods are increasingly being used for data modeling because of their conceptual simplicity and outstanding performance on many tasks. However, the kernel function is often...

On kernel-target alignment (2002)

Nello Cristianini, John Shawe-taylor, Andre Elissee, Jaz Kandola

We introduce the notion of kernel-alignment, a measure of similarity between two kernel functions or between a kernel and a target function. This quantity captures the degree of agreement between a...

Spectral Kernal Methods for Clustering (2002)

Nello Cristianini, John Shawe-Taylor, Jaz Kandola

In this paper we introduce new algorithms for unsupervised learning based on the use of a kernel matrix. All the information required by such algorithms is contained in the eigenvectors of the matrix...