Stochastic Bound Majorization

Recently a majorization method for optimizing partition functions of log-linear models was proposed alongside a novel quadratic variational upper-bound. In the batch setting, it outperformed state-of-the-art firstand second-order optimization methods on various learning tasks. We propose a stochastic version of this bound majorization method as well as a low-rank modification for highdimensional data-sets. The resulting stochastic second-order method outperforms stochastic gradient descent (across variations and various tunings) both in terms of the number of iterations and computation time till convergence while finding a better quality parameter setting. The proposed method bridges firstand secondorder stochastic optimization methods by maintaining a computational complexity that is linear in the data dimension and while exploiting second order information about the pseudo-global curvature of the objective function (as opposed to the local curvature in the Hessian).