Information geometry is a method of exploring the world of information by means of modern geometry. Theories of information have so far been studied mostly by using algebraic, logical, analytical, and probabilistic methods. Since geometry studies mutual relations between elements such as distance and curvature, it should provide the information sciences with powerful tools. Information geometry has emerged from studies of invariant geometrical structure involved in statistical inference. It defines a Riemannian metric together with dually coupled affine connections in a manifold of probability distributions. These structures play important roles not only in statistical inference but also in wider areas of information sciences, such as machine learning, signal processing, optimization, and even neuroscience, not to mention mathematics and physics. (by Shun-ichi Amari. Information Geometry and Its Applications. Vol. 194. Springer, 2016)
References
Shun-ichi Amari and Hiroshi Nagaoka. Methods of information geometry. Vol. 191. American Mathematical Soc., 2007.
Shun-ichi Amari. Information Geometry and Its Applications. Vol. 194. Springer, 2016.
June 27-30, 2016
82J04, Jia Yi Bing Building, 82 Jing Chun Yuan, BICMR
北京大学镜春园82号甲乙丙楼82J04
Bin Dong, Peking University
Zhengchao Wan (万政超,数院12级本,基础专业)
June 27, 09:30-12:00
June 28, 09:30-12:00
June 29, 09:30-12:00; 14:00-16:30
June 30, 14:00-16:30