A Hybrid Algorithm for Convex Semidefinite Optimization

We present a hybrid algorithm for optimizing a convex, smooth function over the cone of positive semidefinite matrices. Our algorithm converges to the global optimal solution and can be used to solve general largescale semidefinite programs and hence can be readily applied to a variety of machine learning problems. We show experimental results on three machine learning problems. Our approach outperforms state-of-the-art algorithms.