专家报告
报告时间：2025年10月31日上午9：00——10：00
报告地点：数学学院A302
报 告 人：赵熙乐
报告题目：Continuous Modeling Perspective for Data Science
报告摘要：The regularizer, which incorporates prior knowledge of images, iscornerstone of inverse imaging problem modelling. In this talk，we will first review the classical regularizers, including total variation regularizer, low-rank regularizer, and nonlocal regularizer. Then we will discuss the limitations of classical hand-crafted regularizers (e.g., expressive capability, applicability, and flexibility). To address the above limitations of classical regularizers, we suggest a unified Continuous Modeling Paradigm for imaging science, which continuously represents discrete data by elegantly leveraging a deep neural network. This paradigm allows us to deconstruct and reconstruct the classical regularizers readily. Extensive experiments demonstrate the promising performance of the continuous modeling perspective.
简介：赵熙乐，电子科技大学教授/博导,中国工业与应用数学学会副秘书长。入选国家高层次青年人才、四川省学术和技术带头人、四川省天府青城计划。第一/通讯在权威期刊SIAM 系列(SIIMS和SISC)和IEEE系列(TPAMI、TIP、TSP、TNNLS等)及顶会CVPR等发表研究工作。研究成果获四川省自然科学一等奖、四川省科技进步一等奖、华为火花奖、计算数学会青年优秀论文竞赛二等奖。主持国自然面上项目、四川省杰出青年科学基金项目、华为项目。