English

A Unified Adaptive Tensor Approximation Scheme to Accelerate Composite Convex Optimization

Optimization and Control 2020-07-06 v3

Abstract

In this paper, we propose a unified two-phase scheme to accelerate any high-order regularized tensor approximation approach on the smooth part of a composite convex optimization model. The proposed scheme has the advantage of not needing to assume any prior knowledge of the Lipschitz constants for the gradient, the Hessian and/or high-order derivatives. This is achieved by tuning the parameters used in the algorithm \textit{adaptively} in its process of progression, which has been successfully incorporated in high-order nonconvex optimization (CartisGouldToint2018, Birgin-Gardenghi-Martinez-Santos-Toint-2017). In general, we show that the adaptive high-order method has an iteration bound of O(1/ϵ1/(p+1))O\left( 1 / \epsilon^{1/(p+1)} \right) if the first pp-th order derivative information is used in the approximation, which has the same iteration complexity as in that of the nonadaptive version in (Baes-2009, Nesterov-2018) where the Lipschitz constants are assumed to be known and the subproblems are assumed to be solved exactly. Thus, our results partially address the problem of incorporating adaptive strategies into the high-order {\it accelerated} methods raised by Nesterov in (Nesterov-2018), although our strategies cannot assure the convexity of the auxiliary problem and such adaptive strategies are already popular in high-order nonconvex optimization (CartisGouldToint2018, Birgin-Gardenghi-Martinez-Santos-Toint-2017). Our numerical experiment results show a clear effect of real acceleration displayed in the adaptive Newton's method with cubic regularization on a set of regularized logistic regression instances.

Keywords

Cite

@article{arxiv.1811.02427,
  title  = {A Unified Adaptive Tensor Approximation Scheme to Accelerate Composite Convex Optimization},
  author = {Bo Jiang and Tianyi Lin and Shuzhong Zhang},
  journal= {arXiv preprint arXiv:1811.02427},
  year   = {2020}
}

Comments

convex optimization, tensor method, acceleration, adaptive method, iteration complexity. arXiv admin note: text overlap with arXiv:1710.04788

R2 v1 2026-06-23T05:06:28.352Z