Ziqiao Wang (汪子乔)

Ph.D. School of Electrical Engineering and Computer Science University of Ottawa [CV][Google Scholar][Semantic Scholar][Twitter][Linkedin] Office: CBY B507 Email: zwang286[AT]uottawa[DOT]ca Grant me the serenity to accept the things I cannot change, the courage to change the things I can, and the wisdom to know the difference. — Reinhold Niebuhr

About Me

I am currently finishing my PhD at the University of Ottawa, where I am very fortunate to have Prof. Yongyi Mao as my PhD advisor. In 2017-18, I was a Master of Applied Science (MASc) student at University of Ottawa. Prior to that, I received my B.E. degree in Electrical Engineering and its Automation from North China Electric Power University (NCEPU) in 2017. Previously, I was a research intern at National Research Council Canada (NRC) in Summer 2019 (full-time) and in Fall 2019 (part-time) where I was mentored by Dr. Harry H.Y. Guo.

My Erdős number is 4 (Wang -> Zhang -> Bhuiyan -> Hsu -> Erdős).

Research Interests

My research interests span the areas of machine learning and statistical learning theory. A common thread in my research is in understanding the generalization theory of deep learning through the lens of information theory. I am also interested in domain adaptation, online learning, reinforcement learning theory and trustworthy machine learning (e.g., privacy, fairness and robustness).

Selected Publications (Full List)

• Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds
  Ziqiao Wang and Yongyi Mao
  NeurIPS 2023

• Tighter Information-Theoretic Generalization Bounds from Supersamples
  Ziqiao Wang and Yongyi Mao
  ICML 2023 (Oral)

• Information-Theoretic Analysis of Unsupervised Domain Adaptation
  Ziqiao Wang and Yongyi Mao
  ICLR 2023

• Over-Training with Mixup May Hurt Generalization
  Zixuan Liu*, Ziqiao Wang* (equal contribution), Hongyu Guo, and Yongyi Mao
  ICLR 2023

• On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
  Ziqiao Wang and Yongyi Mao
  ICLR 2022

Professional Service

• Conference Reviewer: NeurIPS, ICML, ICLR, AISTATS, IJCAI, ISIT
  

• Journal Reviewer: IEEE Transactions on Information Theory (TIT), Transactions on Machine Learning Research (TMLR), IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Journal on Selected Areas in Information Theory (JSAIT)
  

• Organizing Committee Member: IEEE North American School of Information Theory (NASIT) 2024