Inexact Tensor Methods with Dynamic Accuracies

Abstract

In this paper, we study inexact high-order Tensor Methods for solving convex optimization problems with composite objective. At every step of such methods, we use approximate solution of the auxiliary problem, defined by the bound for the residual in function value. We propose two dynamic strategies for choosing the inner accuracy: the first one is decreasing as $1/k^{p+1}$, where $p\ge 1$ is the order of the method and $k$ is the iteration counter, and the second approach is using for the inner accuracy the last progress in the target objective. We show that inexact Tensor Methods with these strategies achieve the same global convergence rate as in the error-free case. For the second approach we also establish local superlinear rates (for $p\ge 2$), and propose the accelerated scheme. Lastly, we present computational results on a variety of machine learning problems for several methods and different accuracy policies.

References in corpus (8)

• Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
• A Universal Catalyst for First-Order Optimization
• Minimizing Uniformly Convex Functions by Cubic Regularization of Newton Method
• Contracting Proximal Methods for Smooth Convex Optimization
• Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization
• Randomized Block Cubic Newton Method
• Fast minimization of structured convex quartics
• A Unified Adaptive Tensor Approximation Scheme to Accelerate Composite Convex Optimization