讲座题目：AI for Incentive-Compatible Insurance: Learning Optimal Indemnity with Lipschitz Networks
主讲人：池义春 教授
主持人：李丹萍 教授
开始时间：2025-12-5 10:00
讲座地址：普陀校区理科大楼A1514
主办单位：统计学院
报告人简介：
池义春，中央财经大学龙马特聘教授。2009年在北京大学获得博士学位后，加入中央财经大学中国精算研究院，历任助理研究员、副研究员、研究员。长期从事精算学与风险管理领域研究，主持四项国家自然科学基金项目及两项教育部人文社科重点研究基地重大课题。在精算学领域权威期刊ASTIN Bulletin、Insurance: Mathematics and Economics、North American Actuarial Journal、Scandinavian Actuarial Journal，金融数学期刊Finance and Stochastics、运筹学期刊European Journal of Operational Research、经济学期刊Journal of Economic Behavior and Organization等发表学术论文三十余篇。2012年获北美非寿险精算协会Charles A. Hachemeister奖，2018年入选中央财经大学首届青年龙马学者项目。现任中国现场统计研究会风险管理与精算分会副理事长、中国保险学会智库专家库专家。
报告内容：
Many optimal insurance design problems with the incentive-compatible (IC) condition lack closed-form solutions and efficient numerical methods. This talk proposes a novel algorithm to obtain numerical solutions of optimal insurance by parameterizing the indemnity function using a Lipschitz Multilayer Perceptron (MLP) architecture. To incorporate the principle of indemnity and the IC condition, we introduce constrained affine transformation layers and a special activation function while preserving the MLP’s universal approximation. Our proposed architecture can be trained using a standard gradient descent algorithm to derive optimal indemnity functions with any given level of error. In addition, our method is applicable for many open but practically important problems including optimal insurance with a dependent background risk, ambiguous loss, and rank-dependent utility.
