Exploring Energy Landscapes by Normalizing Flows



Hao Wu, Tongji University


2021.01.06 09:00-10:00


Room 305, Building No. 5, Science Buildings


Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge. Lacking methods for generating statistically independent equilibrium samples directly, vast computational effort is invested for simulating these system in small steps, e.g., using Molecular Dynamics. Combining normalizing flows and statistical mechanics, we here develop Boltzmann Generators, that are shown to generate statistically independent samples of equilibrium states of representative condensed matter systems and complex polymers. Boltzmann Generators use neural networks to learn a coordinate transformation of the complex configurational equilibrium distribution to a distribution that can be easily sampled. Accurate computation of free energy differences, and discovery of new system states are demonstrated, providing a new statistical mechanics tool that performs orders of magnitude faster than standard simulation methods.


吴昊,于2002年和2007年获清华大学计算机专业学士和博士学位,而后赴德国柏林自由大学数学系从事博士后工作,并兼任柏林Zuse研究所的研究组组长。另外,在德期间以主持人身份承担德国科学基金会DFG与柏林爱因斯坦基金会的科研项目各一项。2018年获国家级人才计划支持,进入同济大学数学科学学院工作。主要从事计算数学、机器学习与计算分子生物学的交叉研究。共发表SCI论文(包括Science、Nat. Commun.和PNAS等知名期刊)和机器学习顶级会议论文(NIPS、UAI等)20余篇。