Keynote Speech 1 and 2

Abstract:   Optimal transport was originally proposed to transport the mass between two probability measures with minimal cost, and has been widely investigated in theory, algorithm and applications. Optimal transport can be taken as a tool for learning distribution transform and designing deep generative model. In this talk, I will briefly introduce the optimal transport from the perspective of machine learning. Then I will present our research on the optimal transport with keypoints-guidance and its extension to the deep generative model, with applications to image synthesis and domain adaptation and generalization.

Abstract:   近年来，随着工业技术和社会生产力的发展,很多系统呈现出复杂性和不确定性两个显著的特征，其中复杂性可以进一步刻画为大规模、网络化和动态性等。计算机仿真是这类复杂系统建模的重要工具，可以用来解决复杂系统管理中的很多问题。系统的复杂性和不确定性也给现今的仿真工具带来了很多挑战,在建模、预测和优化领域都有很多问题亟待解决。包括高性能计算、大数据和人工智能技术在内的很多新兴技术则为解决这些挑战带来了机遇，这些技术与仿真工具的深度融合将是下一代仿真工具研发的关键。