# Tensor Methods for Minimizing Convex Functions with Hölder Continuous Higher-Order Derivatives

@article{Grapiglia2020TensorMF,
title={Tensor Methods for Minimizing Convex Functions with H{\"o}lder Continuous Higher-Order Derivatives},
author={G. N. Grapiglia and Y. Nesterov},
journal={SIAM J. Optim.},
year={2020},
volume={30},
pages={2750-2779}
}
• Published 2020
• Computer Science, Mathematics
• SIAM J. Optim.
In this paper we study p-order methods for unconstrained minimization of convex functions that are p-times differentiable (p ≥ 2) with n-Holder continuous p th derivatives. We propose tensor schemes with and without acceleration. For the schemes without acceleration, we establish iteration complexity bounds of O(e-1/(p+n-1))$for reducing the functional residual below a given e I\in (0,1). Assuming that n is known, we obtain an improved complexity bound of O(e-1/(p+n))$ for the corresponding… Expand
4 Citations
Optimal Combination of Tensor Optimization Methods
• Mathematics, Computer Science
• OPTIMA
• 2020
A general framework allowing to obtain near-optimal oracle complexity for each function in the sum separately is proposed, meaning, in particular, that the oracle for a function with lower Lipschitz constant is called a smaller number of times. Expand
Tensor methods for finding approximate stationary points of convex functions
• Mathematics, Physics
• 2019
In this paper we consider the problem of finding $\epsilon$-approximate stationary points of convex functions that are $p$-times differentiable with $\nu$-H\"{o}lder continuous $p$th derivatives. WeExpand
Optimization Methods for Fully Composite Problems
• Mathematics
• 2021
In this paper, we propose a new Fully Composite Formulation of convex optimization problems. It includes, as a particular case, the problems with functional constraints, max-type minimizationExpand
Smoothness Parameter of Power of Euclidean Norm
• Mathematics, Computer Science
• J. Optim. Theory Appl.
• 2020
This paper proves the Hölder continuity and establishes explicit expressions for the corresponding constants of derivatives of powers of Euclidean norm, and shows that these constants are optimal for odd derivatives and at most two times suboptimal for the even ones. Expand