Hoi-To Wai @ CUHK

Assistant Professor Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong, Hong Kong Email: htwai at se dot cuhk dot edu dot hk Links: My CV, Department Profile, Google Scholar

About Me

I am an Assistant Professor at the Department of Systems Engineering and Engineering Management in The Chinese University of Hong Kong (CUHK). I also received my B. Eng (with first class Honor) and M. Phil. from CUHK, working with Prof. Wing-kin (Ken) Ma in Spring 2010 and 2012, respectively. I received my PhD degree from Arizona State University in Fall 2017, working with Prof. Anna Scaglione. Currently, I am serving the editorial board of IEEE TSIPN and Elsevier's Signal Processing, as well as a member of the IEEE SPS's SPTM-TC and DSI. I am also an organizer for the DEGAS Webinar Series

Besides ASU and CUHK, I have held research positions at LIDS, MIT working with Prof. Asuman E. Ozdaglar, and at Télécom ParisTech, Ecole Polytechnique, working with Prof. Eric Moulines, and at UC Davis as a PhD student with Anna before transferring to ASU. I have received the 2017's Dean's Dissertation Award at ASU's Ira A. Fulton Schools of Engineering (Full Circle), and a Best Student Paper Award from IEEE ICASSP 2018 (paper).

My current research focus is on:

• Graph signal processing and graph learning problem for network science

• Stochastic algorithms for machine learning and distributed signal processing

Check out the Research page for more details.

I am looking for mathematically inclined and motivated students/Postdoc interested in optimization theory for machine learning, reinforcement learning or graph signal processing problems. Please contact me if you are interested. Also consider applying for the HK PhD Fellowship Scheme which offers great support for studying in CUHK.

Recent News

• July, 2024: Sean has received a Best Student Paper Award at IEEE SAM 2024 for his paper On Detecting Low-pass Graph Signals under Partial Observations. This work, done as a part of Sean's FYP, is an extension over our prior work recently accepted by IEEE TSP (with Chenyue and Yiran) for detecting if a set of graph signals is low pass or not without knowing the graph topology, now under partially observed nodes. Congratulations!

• June, 2024: 2 journal papers accepted:

  • “Detecting Low Pass Graph Signals via Spectral Pattern: Sampling Complexity and Applications” at IEEE Transactions on Signal Processing (with Chenyue and Yiran - Congrats to Chenyue to her first journal paper!)  —  we propose a detector for low pass (smooth) graph signals without requiring knowledge of graph topology, giving a data-driven certificate for the application of low pass GSP tools and detector of underlying network dynamics.

• • “Optimal Pricing for Linear-Quadratic Games With Nonlinear Interaction Between Agents” at IEEE Control Systems Letters (with Jiamin and Chenyue - This is Jiamin's FYP work at CUHK and first paper!)  —  we revisited the optimal pricing problem for network game with nonlinear interactions, and showed analytically that assymetric interactions are necessary to achieve maximum profit, this contrasts the previous results on linear interactions where symmetric interactions are sufficient to achieve maximum profit. (\(\alpha = 0.5\) in the figure below refers to symmetric graph)

• May, 2024: 2 papers on performative prediction and contrastive learning accepted at ICML 2024:

• • Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data (with Haitong and Qiang - it's a work Haitong did during his UG study in CUHK!)  —  we propose an effective derivative-free algorithm for tackling the performative risk optimization problem that works with Markovian (i.e., gradually shifted distributions) data.

• • EMC2: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence (with Oscar, Mingyi, Parameswaran and Soumajyoti)  —  we develop an SGD-like algorithm for contrastive learning over a large set of negative samples using MCMC for negative sampling.