Workshop summary: Numerical mathematics in machine learning
Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By John P. Cunningham, Matthias Seeger, Suvrit Sra
Issue Date:June 2009
Previous studies of Non-Parametric Kernel (NPK) learning usually reduce to solving some Semi-Definite Programming (SDP) problem by a standard SDP solver. However, time complexity of standard interior-point SDP solvers could be as high as O(n6.5). Such inte...