On the Optimal Combination of Tensor Optimization Methods
From MaRDI portal
Publication:6334064
DOI10.1007/978-3-030-62867-3_13arXiv2002.01004MaRDI QIDQ6334064FDOQ6334064
Authors: Dmitry Kamzolov, A. V. Gasnikov, Pavel Dvurechensky 
Publication date: 3 February 2020
Abstract: We consider the minimization problem of a sum of a number of functions having Lipshitz -th order derivatives with different Lipschitz constants. In this case, to accelerate optimization, we propose a general framework allowing to obtain near-optimal oracle complexity for each function in the sum separately, meaning, in particular, that the oracle for a function with lower Lipschitz constant is called a smaller number of times. As a building block, we extend the current theory of tensor methods and show how to generalize near-optimal tensor methods to work with inexact tensor step. Further, we investigate the situation when the functions in the sum have Lipschitz derivatives of a different order. For this situation, we propose a generic way to separate the oracle complexity between the parts of the sum. Our method is not optimal, which leads to an open problem of the optimal combination of oracles of a different order.
This page was built for publication: On the Optimal Combination of Tensor Optimization Methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334064)
