Výsledky vyhledávání - "Liu, Zhuanghua"

Report

Incremental Gauss--Newton Methods with Superlinear Convergence Rates

Autor: Zhou, Zhiling, Liu, Zhuanghua, Liu, Chengchang, Luo, Luo

This paper addresses the challenge of solving large-scale nonlinear equations with H\"older continuous Jacobians. We introduce a novel Incremental Gauss--Newton (IGN) method within explicit superlinear convergence rate, which outperforms existing met

Externí odkaz: http://arxiv.org/abs/2407.03195

Zobrazit plný text záznamu

Report

Differentiable Cluster Graph Neural Network

Autor: Dong, Yanfei, Dupty, Mohammed Haroon, Deng, Lambert, Liu, Zhuanghua, Goh, Yong Liang, Lee, Wee Sun

Graph Neural Networks often struggle with long-range information propagation and in the presence of heterophilous neighborhoods. We address both challenges with a unified framework that incorporates a clustering inductive bias into the message passin

Externí odkaz: http://arxiv.org/abs/2405.16185

Zobrazit plný text záznamu

Report

Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates

Autor: Liu, Zhuanghua, Luo, Luo, Low, Bryan Kian Hsiang

We consider the finite-sum optimization problem, where each component function is strongly convex and has Lipschitz continuous gradient and Hessian. The recently proposed incremental quasi-Newton method is based on BFGS update and achieves a local su

Externí odkaz: http://arxiv.org/abs/2402.02359

Zobrazit plný text záznamu

Report

Decentralized Sum-of-Nonconvex Optimization

Autor: Liu, Zhuanghua, Low, Bryan Kian Hsiang

We consider the optimization problem of minimizing the sum-of-nonconvex function, i.e., a convex function that is the average of nonconvex components. The existing stochastic algorithms for such a problem only focus on a single machine and the centra

Externí odkaz: http://arxiv.org/abs/2402.02356

Zobrazit plný text záznamu

Report

Towards Sharper First-Order Adversary with Quantized Gradients

Autor: Liu, Zhuanghua, Tsang, Ivor W.

Despite the huge success of Deep Neural Networks (DNNs) in a wide spectrum of machine learning and data mining tasks, recent research shows that this powerful tool is susceptible to maliciously crafted adversarial examples. Up until now, adversarial

Externí odkaz: http://arxiv.org/abs/2002.02372

Zobrazit plný text záznamu