吕力遥

邮 件: lyuliyao@ustc.edu.cn
所属单位:人工智能与数据科学学院
个人主页:http://lyuliyao.com/
主要研究方向:多尺度建模与机器学习,科学机器学习与数值算法,基于共识的无梯度优化与采样。
个人简介:吕力遥,中国科学技术大学人工智能与数据科学学院特任教授。主要研究方向包括科学智能(AI for Science)、机器学习驱动的多尺度建模与科学计算、随机优化与控制。2020年本科毕业于苏州大学,2025年获美国密歇根州立大学计算数学、科学与工程博士学位。曾任美国加州大学洛杉矶分校(UCLA)Hedrick Assistant Adjunct Professor。围绕微分方程的深度学习求解、具有物理一致性的分子体系粗粒化建模及无梯度随机控制开展系统研究,在 Physical Review Letters、SIAM Journal on Scientific Computing, Journal of Computational Physics、SIAM Multiscale Modeling & Simulation、ICML 等国际重要期刊和会议发表论文十余篇,代表性成果获 Physical Review Letters 编辑推荐(Editor’s Suggestion)。
近几年代表论著:
[1] Lyu, Liyao, and Huan Lei. "Construction of coarse-grained molecular dynamics with many-body non-Markovian memory." Physical Review Letters 131, no. 17 (2023)
[2] Lyu, Liyao, and Huan Lei. "Consensus-based adaptive sampling and approximation for high-dimensional energy landscapes." SIAM Journal on Scientific Computing 48, no. 5 (2026): B751-B775.
[3] Lyu, Liyao, and Jingrun Chen. "Consensus based stochastic optimal control." In Forty-second International Conference on Machine Learning. 2025.
[4] Lyu, Liyao, and Huan Lei. "On the generalization ability of coarse-grained molecular dynamics models for nonequilibrium processes." Multiscale Modeling & Simulation 23, no. 2 (2025): 816-837.
[5] Lyu, Liyao, Zhen Zhang, Minxin Chen, and Jingrun Chen. "MIM: A deep mixed residual method for solving high-order partial differential equations." Journal of Computational Physics 452 (2022): 110930.
