Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Smooth Operators
AU - Grunewalder, S.
AU - Gretton, A.
AU - Shawe-Taylor, J.
PY - 2013/6/16
Y1 - 2013/6/16
N2 - We develop a generic approach to form smooth versions of basic mathematical operations like multiplication, composition, change of measure, and conditional expectation, among others. Operations which result in functions outside the reproducing kernel Hilbert space (such as the product of two RKHS functions) are approximated via a natural cost function, such that the solution is guaranteed to be in the targeted RKHS. This approximation problem is reduced to a regression problem using an adjoint trick, and solved in a vector-valued RKHS, consisting of continuous, linear, smooth operators which map from an input, real-valued RKHS to the desired target RKHS. Important constraints, such as an almost everywhere positive density, can be enforced or approximated naturally in this framework, using convex constraints on the operators. Finally, smooth operators can be composed to accomplish more complex machine learning tasks, such as the sum rule and kernelized approximate Bayesian inference, where state-of-the-art convergence rates are obtained.
AB - We develop a generic approach to form smooth versions of basic mathematical operations like multiplication, composition, change of measure, and conditional expectation, among others. Operations which result in functions outside the reproducing kernel Hilbert space (such as the product of two RKHS functions) are approximated via a natural cost function, such that the solution is guaranteed to be in the targeted RKHS. This approximation problem is reduced to a regression problem using an adjoint trick, and solved in a vector-valued RKHS, consisting of continuous, linear, smooth operators which map from an input, real-valued RKHS to the desired target RKHS. Important constraints, such as an almost everywhere positive density, can be enforced or approximated naturally in this framework, using convex constraints on the operators. Finally, smooth operators can be composed to accomplish more complex machine learning tasks, such as the sum rule and kernelized approximate Bayesian inference, where state-of-the-art convergence rates are obtained.
M3 - Conference contribution/Paper
VL - 28
SP - 1184
EP - 1192
BT - Proceedings of the 30th International Conference on Machine Learning
PB - PMLR
ER -