信息来源: 发布日期:2024-12-04 浏览次数:
姓名:
汪子乔
职称:
助理教授
学科:
计算机科学与技术
专业:
研究方向:
机器学习、统计学习原理和信息论
电子邮件:
ziqiaowang@tongji.edu.cn
通讯地址:
上海市曹安公路4800号智信馆
汪子乔,同济大学计算机科学与技术学院助理教授,博士毕业于加拿大渥太华大学。入选国家级海外高层次青年人才、上海市白玉兰海外高层次青年人才,主持国家自然科学基金青年基金项目1项,参与国家科技部重点研发计划1项。研究方向为机器学习基础理论、大模型学习理论与算法以及信息论。近几年主要成果发表在人工智能、机器学习及数据挖掘等相关领域国际顶级会议,涵盖NeurIPS、ICML、ICLR、UAI、AAAI、KDD、WWW等,博士论文被提名2025年加拿大人工智能协会最佳博士论文奖,以及提名2025年渥太华大学总督学术奖章和Pierre Laberge论文奖。曾担任 ICLR 2026 会议领域主席(Area Chair),2025年中国具身智能大会注册主席,以及2024 年 IEEE 北美信息论暑期学校(NASIT)联合程序主席。
个人主页:https://ziqiaowanggeothe.github.io/
导师信息:https://tongji.teacher.360eol.com/teacherBasic/preview?teacherId=36636
近年代表性论文如下:
§Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive ApproachHaiyun He, Yepeng Liu, Ziqiao Wang, Yongyi Mao, and Yuheng BuNeurIPS 2025
§Generalization in Federated Learning: A Conditional Mutual Information FrameworkZiqiao Wang, Cheng Long, and Yongyi MaoICML 2025
§Generalization Bounds via Conditional f-InformationZiqiao Wang and Yongyi MaoNeurIPS 2024
§On f-Divergence Principled Domain Adaptation: An Improved FrameworkZiqiao Wang and Yongyi MaoNeurIPS 2024
§Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal StatesZiqiao Wang and Yongyi MaoUAI 2024
§Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization BoundsZiqiao Wang and Yongyi MaoNeurIPS 2023
§Tighter Information-Theoretic Generalization Bounds from SupersamplesZiqiao Wang and Yongyi MaoICML 2023 (Oral)
§Information-Theoretic Analysis of Unsupervised Domain AdaptationZiqiao Wang and Yongyi MaoICLR 2023
§Over-Training with Mixup May Hurt GeneralizationZixuan Liu*, Ziqiao Wang*, Hongyu Guo, and Yongyi MaoICLR 2023
§On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and ImplicationsZiqiao Wang and Yongyi MaoICLR 2022
上一条: 汪昱
下一条: 熊明亮