Výsledky vyhledávání - "Zhang, Dewei"

Dissertation/ Thesis

On deterministic and stochastic optimization algorithms for problems with Riemannian manifold constraints

Autor: Zhang, Dewei

Optimization methods have been extensively studied given their broad applications in areas such as applied mathematics, statistics, engineering, healthcare, business, and finance. In the past two decades, the fast growth of machine learning and artif

Externí odkaz: http://rave.ohiolink.edu/etdc/view?acc_num=osu164017985264468

Zobrazit plný text záznamu

Report

Achieving Linear Speedup in Non-IID Federated Bilevel Learning

Autor: Huang, Minhui, Zhang, Dewei, Ji, Kaiyi

Federated bilevel optimization has received increasing attention in various emerging machine learning and communication applications. Recently, several Hessian-vector-based algorithms have been proposed to solve the federated bilevel optimization pro

Externí odkaz: http://arxiv.org/abs/2302.05412

Zobrazit plný text záznamu

Report

Riemannian Stochastic Gradient Method for Nested Composition Optimization

Autor: Zhang, Dewei, Tajbakhsh, Sam Davanloo

This work considers optimization of composition of functions in a nested form over Riemannian manifolds where each function contains an expectation. This type of problems is gaining popularity in applications such as policy evaluation in reinforcemen

Externí odkaz: http://arxiv.org/abs/2207.09350

Zobrazit plný text záznamu