2020年1月12日-16日， 由香港城市大学陈汉夫教授、博洛尼亚大学Fiorella Sgallari教授、香港浸会大学台雪成教授、北京应用物理与计算数学研究所魏素花教授一起组织的数据科学，机器学习，计算物理中的高效算法研讨会（Efficient Algorithms in Data Science, Learning and Computational Physics）将在论坛举行，会议有48位来自中国、美国、德国、意大利等国家的高等院校或研究机构的师生参加。会议期间就数据科学，机器学习，计算物理中的高效算法问题展开研讨，届时将举行30场相关学术报告。
Most of the tasks in data science, machine learning, computational physics, and inverse problems can be cast into data-driven constrained optimization problems. Such optimization problems could involve nonlinear, non-differentiable, and non-convex objectives and constraints. Though the past decades have seen tremendous advances in both theories and computational algorithms for optimization, efficiently solving large-scale nonlinear, non-differentiable, and non-convex optimization problems, and quantifying the uncertainty in their solution remains challenging. On the other hand, the exponential increase in the quantity of measurements and data holds tremendous promise for data-driven scientific discoveries. However, much data remains unused as optimization---a systematic tool to infer knowledge from data---is unable to scale up to the quantity of data being generated. Thus, there is a critical need to develop computational and data scalable strategies to tackle the challenge of large-scale data-driven optimization problems in order to continue the pace of scientific discoveries and to promote the progress of science. Machine learning is related to data science, but it also needs special attention to knowledge based concepts and thus need algorithms that can handle large data and also produce usable knowledge. Efficient algorithms for machine learning will be an important part of this conference. In addition, many of the algorithms used for big data and machine learning rooted back to many traditional algorithms used for computational science. Thus, we will also bring in new and traditional computational physics into this workshop. This workshop will provide a venue for dialogue and synergies between theoreticians in optimization and the computational scientists in the field so that the gap between the researchers working on the fundamentals and those working on real-life applications can be reduced.
Raymond Chan (CityU, HK),
Fiorella Sgallari, University of Bologna
Xue-Cheng Tai (Baptist Univ),
Suhua Wei (Inst of Applied Physics and Computational Math)