报告题目:Stochastic approximation of functions by neural networks in kernel-regression formations
报告人:孙兴平
讲座时间:2026年11月15日(周日) 16:00
地点:综合楼644会议室
报告人简介:
孙兴平,现任密苏里州立大学杰出教授,长期从事统计机器学习与径向基函数等领域的研究。在德克萨斯A&M大学、范德堡大学、英国莱斯特大学,复旦大学等机构多次受邀访问。他在《Mathematics of Computation》《SIAM Journal on Numerical Analysis》等权威期刊发表大量论文,主持多项美国国家科学基金会(NSF)及国际合作研究项目,并积极参与学术服务,担任多个期刊编委及会议组织者。此外,他曾任密苏里州立大学自然科学与应用科学学院副院长(2012–2015),并多次获得教学与科研奖项。
报告摘要:Universal approximation theorems in the feld of machine learning state that neural networks with some common mathematical structures are employable for the purpose of approximating continuous functions. However, most of these theorems are non-constructive in nature, and therefore have left ample rooms for improvement. In this talk, we propose and study a constructive method for stochastic approximation of functions by neural networks, which features kernel-regression formations.
