Although deep learning models are highly effective for various tasks, such as detection and classification, the high computational cost prohibits the deployment in scenarios where either memory or computational resources are limited. In this paper, we focus on model compression and acceleration of deep models. We model a low bit quantized neural network as a constrained optimization problem. Th...

This paper studies convergence properties of inexact variants of the proximal point algorithm when applied to a certain class of nonmonotone mappings. The presented algorithms allow for constant relative errors, in the line of the recently proposed hybrid proximal-extragradient algorithm. The main convergence result extends a recent work of the second author, where exact solutions for the proxi...

The main strategy of this paper is intended to speed up the convergence inertial Mann iterative method and further it through normal S-iterative for a certain class nonexpansive-type operators that are linked with variational inequality problems. Our new theory permits us settle down difficulty unification Korpelevich’s extragradient method, Tseng’s extragardient subgardient solving problems an...

<p style='text-indent:20px;'>In this paper, we introduce and study a modified extragradient algorithm for approximating solutions of certain class split pseudo-monotone variational inequality problem in real Hilbert spaces. Using our proposed algorithm, established strong convergent result the aforementioned problem. Our is obtained without prior knowledge Lipschitz constant operator used...

Pointwise and ergodic iteration-complexity results for the proximal alternating direction method of multipliers (ADMM) for any stepsize in (0, (1 + √ 5)/2) have been recently established in the literature. In addition to giving alternative proofs of these results, this paper also extends the ergodic iteration-complexity result to include the case in which the stepsize is equal to (1+ √ 5)/2. As...