讲座信息

讲座信息

您当前的位置: 讲座信息
20190424 焦雨领:Deep Generative Learning via Variational Gradient Flow
时间:2019-04-23

报告时间:2019年4月24日 14:00-15:00

报告地点:明德主楼1016会议室

报告主题:Deep Generative Learning via Variational Gradient Flow


报告摘要:

  Learning underlying distribtuation from data is one of the fundmental task in statistics and machine learning. In this talk, We propose a general framework to learn deep generative models via Variational Gradient Flow (VGrow) on probability spaces. The evolving distribution that asymptotically converges to the target distribution is governed by a vector field, which is the negative gradient of the _first variation of the f-divergence between them. We prove that the evolving distribution coincides with the pushforward distribution through the infinitesimal time composition of residual maps that are perturbations of the identity map along the vector field. The vector field depends on the density ratio of the pushforward distribution and the target distribution, which can be consistently learned from a binary classification problem. Connections of our proposed VGrow method with other popular methods, such as VAE, GAN and ow-based methods, have been established in this framework, gaining new insights of deep generative learning. We also evaluated several commonly used divergences, including Kullback-Leibler, Jensen-Shannon, Jeffreys divergences as well as our newly discovered logD divergence which serves as the objective function of the logD-trick GAN. Experimental results on benchmark datasets demonstrate that VGrow can generate high-fidelity images in a stable and efficient manner, achieving competitive performance with state-of-the-art GANs.


  报告者简介:

焦雨领,2014年毕业于武汉大学数学与统计学院, 现就职于中南财经政法大学统计与数学学院统计学系,文澜学者。主要从事数据科学(机器学习、统计计算、高维统计推断、反问题等)方面研究。主持国家自然科学基金面上项目、青年项目和湖北省自然科学基金面上项目各一项,中央高校研究项目3项。在包括 SIAM Journal on Numerical Analysis, SIAM Journal on Scientific Computing, Journal of Machine Learning Research, Applied and Computational Harmonic Analysis, Inverse Problems, IEEE Transactions on Signal Processing, IEEE Transactions on Geoscience and Remote Sensing, Journal of Scientific Computing, Advanced in Computational Mathematics 等在内的国际一类、二类期刊上发表30余篇SCI论文并制作了多个MATLAB/R软件包。