首页

主题Quantum Gradient Descendent Algorithm

主讲人香港理工大学  张国锋副教授

主持人:经济数学学院 车茂林博士

2019712日(星期300--400

:西南财经大学柳林校区通博楼B412
主办单位:经济数学学院  科研处

内容提要

The gradient descendent algorithm is an iterated optimization algorithm which finds a local minimum of a function by searching along the steepest descent direction of the function. The gradient descendent algorithm is a simple optimization method which has wide applications---a famous example being the backpropagation algorithm in the training of neural networks. In this talk, we discuss a quantum version of the gradient descendent algorithm. We first touch on the fundamentals of quantum mechanics, such as states, system variables, composite systems, partial trace and quantum measurement, then we discuss quantum Fourier transform which is key to quantum phase estimation; finally, we present the quantum gradient descendent algorithm.

梯度下降法是一个迭代优化算法,旨在沿函数的最速下降方向寻找函数的局部最小值。梯度下降法有着广泛的应用,比如,神经网络训练过程中的反向传播方法。在这一报告中,我们考虑梯度下降法的量子版本。首先,我们引入量子理学的一些基本概念:态、系统变量、复合系统、部分跟踪和量子测量。然后,我们讨论了量子傅立叶变换,这是量子相位估计的关键。最后,我们研究了量子梯度下降方法。


主讲人简介

Guofeng Zhang received his B.Sc. degree and M.Sc. degree from Northeastern University, Shenyang, China, in 1998 and 2000 respectively. He received a Ph.D. degree in Applied Mathematics from the University of Alberta, Edmonton, Canada, in 2005. During 2005–2006, he was a Postdoc Fellow at the University of Windsor, Windsor, Canada. He joined the School of Electronic Engineering of the University of Electronic Science and Technology of China, Chengdu, China, in 2007. From April 2010 to December 2011 he was a Research Fellow at the Australian National University. He is currently an Associate Professor in the Department of Applied Mathematics at the Hong Kong polytechnic University. His research interests include quantum information and control, sampled-data control and nonlinear dynamics.

张国锋分别于1998年和2000年在东北大学获得学士学位和硕士学位,于2005年在加拿大阿尔伯塔大学的应用数学系获得博士学位。2005年至2006年,在加拿大温莎大学从事博士后研究。2007年入职电子科技大学的电子工程系。20104月至201111月,在澳大利亚国立大学担任研究助理。现阶段为香港理工大学应用数学系的副教授。研究兴趣为量子信息于控制、样本数据控制和非线性动力学。