大会报告人
Plenary Talk 1：
Xu, Zongben
Academician of Chinese Academy of Sciences
Professor, School of Mathematics and Statistics, Xi'an Jiaotong University
Title: 如何学习学习方法论? ——兼论大模型的本质
Abstract:
学习方法论是指导、管理学习者如何学习/完成学习任务的一般原则与方法学。在机器学习从人工化，走向自动化,迈向自主化的大趋势下，让机器学会人类的学习方法论，或者更严格地说，学会模拟学习方法论(Simulate Learning Methodology，SLeM)成为AI发展的必需，具有重大的科学意义和应用价值。本报告严格定义学习学习方法论问题，提出SLeM的元学习模式和“超参数化”求解方法，建立SLeM泛化性理论，并应用于多个机器学习自动化问题,展示其有效性。
我们说明：SLeM是实现通用人工智能的主要途径,本质是学习从任务到方法的映照,数学上是无穷维空间上的机器学习问题。以ChatGPT为代表的大模型本质上正是在以“蛮力出奇迹”的方式实现SLeM，而相比较而言，SLeM 的元学习模式则以“低维近似的方式”实现SLeM。由此可见,SLeM 是非常值得关注和深入研究的新方向。
Biography：
徐宗本，中国科学院院士，数学家、信号与信息处理专家、西安交通大学教授。
主要从事应用数学、机器学习、数据建模基础理论研究。曾提出稀疏信息处理的L(1/2)正则化理论,为稀疏微波成像提供了重要基础；发现并证明机器学习的“徐-罗奇”定理, 解决了神经网络与模拟演化计算中的一些困难问题,为非欧氏框架下机器学习与非线性分析提供了普遍的数量推演准则; 提出基于视觉认知的数据建模新原理与新方法，形成了聚类分析、判别分析、隐变量分析等系列数据挖掘核心算法, 并广泛应用于科学与工程领域。曾获国家自然科学二等奖、国家科技进步二等奖、陕西省最高科技奖; 国际IAITQM 理查德.普莱斯(Richard Price)数据科学奖;中国陈嘉庚信息技术科学奖、华罗庚数学奖、苏步青应用数学奖；曾在2010年世界数学家大会上作45分钟特邀报告。
曾任西安交通大学副校长，现任人工智能与数字經济广东省实验室(琶洲实验室(黄埔)主任、西安数学与数学技术研究院院长、陕西国家应用数学中心主任、大数据算法与分析技术国家工程实验室主任。是国家大数据专家咨询委员会委员、国家新一代人工智能战略咨询委员会委员。
Plenary Talk 2：
Bühlmann, Peter Lukas
Professor at the Department of Mathematics at ETH Zürich
President of the Institute of Mathematical Statistics (IMS)
Title: Causal inspired and robust statistical machine learning
Abstract:
Robust, reliable and interpretable machine learning is a big emerging theme in data science and artificial intelligence, complementing the development of standard black box prediction algorithms. New mathematical connections between distributional robustness and causality provide methodological paths for improving the reliability and understanding of machine learning algorithms, with wide-ranging prospects for various applications.
Biography：
Peter Bühlmann has been Full Professor of Mathematics at the ETH Zurich since 1 October 2004. He was born on April 12, 1965, citizen from Sempach (Switzerland), and studied mathematics at the ETH Zurich (1985-1990). In 1993, he received his doctoral degree in mathematics (statistics) from the ETH Zurich. From 1994-1995 he worked as a postdoc in the Department of Statistics at the University of California at Berkeley. Following this he spent two more years, from 1995-1997, at the U.C. Berkeley as Neyman assistant professor. From 1997-2001 he was Assistant Professor and from 2001-2004 Associate Professor of Mathematics at the ETH Zurich. His main research is in the field of statistics, with connections to machine learning, bioinformatics and computational biology. Of special interest are the areas of high-dimensional statistics, computational methods for large-scale modeling, and causal inference.
Plenary Talk 3：
Cai, T. Tony
The Daniel H. Silberberg Chair Professor at the Wharton School of the University of Pennsylvania
President-Elect of the Institute of Mathematical Statistics (IMS)
Title: When Statistics Meets Computing: A Few Interesting Problems and Challenges
Abstract:
In the conventional statistical framework, the goal is to develop optimality theory and optimal statistical procedures, where the optimality is understood with respect to the sample size and parameter space. However, in many contemporary applications, nonstatistical concerns such as computational, communication, and privacy constraints associated with the statistical procedures come to the forefront. A fundamental question in Data Science is: How to make optimal statistical inference under these nonstatistical constraints?
In this talk, we discuss some recent advances on differentially private learning, distributed learning under communication constraints, and interplay between statistical accuracy and computational efficiency in a few specific settings. The results show some interesting and novel phenomena and point to directions that are worthy further investigation.
Biography：
蔡天文 (Tony Cai) 现任美国宾夕法尼亚大学沃顿商学院Daniel H. Silberberg讲席教授及统计与数据科学教授；宾夕法尼亚大学应用数学及计算科学教授；宾夕法尼亚大学医学院生物统计, 流行病学, 及信息学系资深学者。2017-2020年任沃顿商学院副院长. 2006年当选国际数理统计学会会士。2008年获得世界统计学考普斯奖（COPSS Presidents' Award), 2017年当选泛华统计学会(ICSA)主席, 2019年获泛华统计学会杰出成就奖。曾任国际统计学顶尖刊物统计年刊 (Annals of Statistics) 主编，及多个权威学术期刊的编委会成员。蔡教授的主要研究方向是大数据分析, 包括机器学习、高维统计、大规模统计推断、统计决策论、函数数据分析、非参数函数估计、以及在基因组与金融工程的应用。他自2000年以来，连续8次获得美国国家科学基金会基金，2012年及2017年获得美国国家卫生研究院基金，2016年获得沃顿商学院全球倡议基金。蔡教授于1996年毕业于康奈尔大学，获得博士学位，师从美国科学院院士劳伦斯.布朗。
Plenary Talk 4：
Ding, Jian
Chair Professor, School of Mathematical Sciences, Peking University
Title: Recent progress on random graph matching problems
Abstract:
A basic goal for random graph matching is to recover the vertex correspondence between two correlated graphs from an observation of these two unlabeled graphs. Random graph matching is an important and active topic in combinatorial statistics: on the one hand, it arises from various applied fields such as social network analysis, computer vision, computational biology and natural language processing; on the other hand, there is also a deep and rich theory that is of interest to researchers in statistics, probability, combinatorics, optimization, algorithms and complexity theory. Recently, extensive efforts have been devoted to the study for matching two correlated Erdős–Rényi graphs, which is arguably the most classic model for graph matching. In this talk, we will review some recent progress on this front, with emphasis on the intriguing phenomenon on (the presumed) information-computation gap. In particular, we will discuss progress on efficient algorithms thanks to the collective efforts from the community. We will also point out some important future directions, including developing robust algorithms that rely on minimal assumptions on graph models and developing efficient algorithms for more realistic random graph models. This is based on joint works with Hang Du, Shuyang Gong, Zhangsong Li, Zongming Ma, Yihong Wu and Jiaming Xu.
Biography：
丁剑，现任北京大学数学科学学院讲席教授，曾任宾夕法尼亚大学Gilbert Helman讲席教授，宾夕法尼亚大学沃顿商学院副教授、芝加哥大学统计系助理教授、副教授。丁剑老师主要研究领域是概率论，尤其关注统计物理学与计算机科学的交叉。他于2002年至2006年就读于北京大学，获学士学位。此后赴美学习，于2011年获美国加州大学伯克利分校博士学位，曾获Rollo Davidson Prize, Alfred P. Sloan Fellowship, NSF Career Award。