学术讲座

12月7日 | 许左权:State-dependent temperature control for Langevin diffusions

时   间:2023年12月7日 10:00-11:30

地   点:普陀校区理科大楼A1514

报告人:许左权香港理工大学副教授

主持人:石芸华东师范大学副教授

摘   要:

<img class="akeylayout_img"tudy the temperature control problem for Langevin diffusions in the context of non-convex optimization. The classical optimal control of such a problem is of the bang-bang type, which is overly sensitive to errors. A remedy is to allow the diffusions to explore other temperature values and hence smooth out the bang-bang control. We accomplish this by a stochastic relaxed control formulation incorporating randomization of the temperature control and regularizing its entropy. We derive a state-dependent, truncated exponential distribution, which can be used to sample temperatures in a Langevin algorithm, in terms of the solution to an HJB partial differential equation. We carry out a numerical experiment on a one-dimensional baseline example, in which the HJB equation can be easily solved, to compare the performance of the algorithm with three other available algorithms in search of a global optimum. This is a joint work with Xuefeng Gao, The Chinese University of Hong Kong and Xun Yu Zhou, Columbia University.

报告人简介:

许左权博士现任教于香港理工大学应用数学系,主要从事金融数学、保险精算、随机控制及机器学习等研究,多次受邀于世界著名学术机构及学术会议上作学术报告,主持多项国家自然科学基金及香港研究资助局项目。其主要学术成果发表在 Mathematical Finance, Operations Research, Annals of Applied Probability, Finance and Stochastics, SIAM Journal on Financial Mathematics,SIAM Journal on Control and Optimization,Mathematics of Operations Research,Insurance: Mathematics and Economics 等国际著名学术期刊上。许博士曾先后就读于南开大学、北京大学、香港中文大学,曾任英国牛津大学数学研究所野村金融数学研究员及 Oxford-Man 研究所通讯研究员,现为 Mathematics of Operations Research,Digital Finance 等国际期刊编委。


发布者:张瑛发布时间:2023-12-04浏览次数:164