General cost functions for support vector regression.

By Alex Smola, Bernhard Schölkopf, K. Müller, T. Downs, Marcus Frean, Marcus R. Gallagher. 1998

How researchers see this paper

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

Citations in the corpus

Fastfood: Approximate Kernel Expansions in Loglinear Time (2014, background): “This allows us to identify P † P from k and vice versa (Smola et al., 1998a; Girosi, 1998; Girosi et al., 1995; Girosi and Anzellotti, 1993; Wahba, 1990).”
Learning drifting concepts: Example selection vs. example weighting (2004, unknown): “(3), the empirical risk of the SVM solution is measured with respect to a linear loss function, but the support vector algorithm is not restricted to the case of linear loss functions, but can be extended to broader classes of loss functions (e.g. see [28]).”
A Tutorial on Support Vector Machines for Pattern Recognition (1998, background): “…and Müller, 1998a; Smola and Schölkopf, 1998), shown connections to regularization theory (Smola, Schölkopf and Müller, 1998b; Girosi, 1998; Wahba, 1998), and shown how SVM ideas can be incorporated in a wide range of other algorithms (Schölkopf, Smola and Müller, 1998b; Schölkopf et al, 1998c).”
Advances in Large Margin Classifiers (2000, methodology): “…Large Margin Classifiers class of functions that the estimate is chosen from are intimately related (Girosi et al., 1993; Smola and Schölkopf, 1998a; Smola et al., 1998): the SV algorithm is equivalent to minimizing the regularized risk Rreg(f) on the set of functions f(x) = ∑ i αik(xi,x) + b,…”
Structural Modelling with Sparse Kernels (2002, background): “Girosi (1997) and Smola (1998) have shown that kernel methods can be placed in a regularisation framework, which guarantees their well posedness; Support Vector Machines (SVMs) (Vapnik, 1995) and Gaussian Processes (GPs) (Rasmussen, 1996) are examples.”
A tutorial on support vector regression (2004, unknown): “One can show that for practical implementations [Smola et al., 1998b] one can solve optimization problems using nearly arbitrary convex cost functions as ef(cid:2)ciently as the special case of " (cid:150)insensitive loss functions.”
Support Vector Regression (2007, background): “Most algorithms for SVR [19, 11, 20, 21] require that the training samples be delivered in a single batch.”