We are happy to announce that on Monday, May 21 2018, Prof. Yurii Nesterov will be speaking on ‘‘Relative smoothness condition and its application to third-order methods’’ as part of our CORE Seminar series.
The official abstract of the talk is as follows:
In this talk, we show that the recently developed relative smoothness condition can be used for constructing implementable third-order methods for Unconstrained Convex Optimization. At each iteration of these methods, we need to solve an auxiliary problem of minimizing a convex multivariate polynomial, which is a sum of the third-order Taylor approximation and a regularization term. It appears that this nontrivial nonlinear optimization problem can be solved very efficiently by a gradient-type minimization method based on the relative smoothness condition. Its linear rate of convergence depends only on absolute constant. This result opens a possibility for practical implementation of the third-order methods.
The talk will be at Smith Hall (SMI) 205, at 4:00 PM.