| Semidefinite Programming by Perceptron Learning (2008) | |||||||||||||||
Abstract | |||||||||||||||
| 1 Introduction Semidefinite programming (SDP) is one of the most active research areas in optimisation. Its appeal derives from important applications in combinatorial optimisation and control theory, from the recent development of efficient algorithms for solving SDP problems and the depth and elegance of the underlying optimisation theory [14], which covers linear, quadratic, and second-order cone programming as special cases. Recently, semidefinite programming has been discovered as a useful toolkit in machine learning with applications ranging from pattern separation via ellipsoids [4] to kernel matrix optimisation [5] and transformation invariant learning [6]. | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||