Vincent Y. F. Tan 陈延福 (Pronouns: he/him/his/他)

Images courtesy of Dave Lee (UCO, NUS)

Professor, Department of Mathematics, Department of Electrical and Computer Engineering (ECE), National University of Singapore (NUS) Affiliate, Institute of Operations Research and Analytics (IORA), Institute of Data Science (IDS) Office: S17-05-20 (Mathematics) and E4-06-06 (ECE) Phone: (65) 6516-2133 Email: vtan @ nus. edu. sg My Curriculum Vitae. My Google Scholar Profile. My Erdős number is 3 (Tan -> Willsky -> Bollobás -> Erdős).

News (Archive)

• Advertisement: Looking to hire motivated postdocs. Please see this advertisement for more details.


• Sep 2023: Promoted to professor with retrospective effect from July 1st, 2023. Thanks to my colleagues in the Maths department and ECE department. Thanks to my students (undergraduate, graduate), research assistants, postdocs, collaborators and, most importantly, my wife Huili Guo and my family for the support over the past few years.


• Sep 2023: Paper titled Learning Regularized Monotone Graphon Mean-Field Games accepted to NeurIPS 2023. Congrats to Fengzhuo!


• Sep 2023: Paper titled Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits accepted to the Transactions on Machine Learning Research. Joint work with Zixin Zhong and Wang Chi Cheung. In this paper, we study the Pareto frontier of two archetypal objectives in multi-armed bandits, namely, regret minimization (RM) and best arm identification (BAI) with a fixed horizon. We are delighted that this is a TMLR paper chosen to be one with "featured certification".


• Sep 2023: Paper titled "BLINK: Link Local Differential Privacy for Graph Neural Networks via Bayesian Estimation" accepted by the ACM Conference on Computer and Communications Security (CCS). CCS is the flagship annual conference of the Special Interest Group on Security, Audit and Control (SIGSAC) of the Association for Computing Machinery (ACM). Joint work with former FYP student Xiaochen Zhu and his co-advisor Xiaokui Xiao.


• Aug 2023: Invited to serve as an Area Chair of ICLR 2024.


• Jul 2023: Posted a paper AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models. Joint work with Jiachun Pan, Hanshu Yan and co-authors.


• Jul 2023: Paper on Deep Unrolling for Nonconvex Robust Principal Component Analysis accepted to MLSP 2023. Joint work with Maths HYP student Elizabeth Tan and collaborators Caroline Chaux and Emmanuel Soubies.


• Jul 2023: Traveling to the Data Science: Probabilistic and Optimization Methods workshop at ICTS, Bangalore.


• Jun 2023: Posted a working draft on DragDiffusion in which we harness diffusion models for interactive point-based image editing. We leverage large-scale pretrained diffusion models to vastly improve the applicability of interactive point-based editing in real world scenarios. This is done by optimizing the diffusion latent to achieve precise spatial control. Work done by Yujun Shi and co-authors. The project page can be found here.


• Jun 2023: Congratulations to FYP student Xiaochen Zhu for being awarded the first place in the 2023 SIGMOD student research competition in the undergraduate category. This is for his work on Link Local Differential Privacy in GNNs via Bayesian Estimation.


• Jun 2023: Congratulations to FYP students Xiaochen Zhu and He Yuan for winning prestigious Outstanding Undergraduate Researcher Prizes.


• Jun 2023: Congratulations to former Ph.D. student Zixin Zhong for winning the Louis Chen Hsiao Yun Best Dissertation Prize. This prize is awarded annually to the student with the best Ph.D. thesis in mathematics and its applications.


• Jun 2023: Congratulations to Ph.D. student Pan Jiachun for successfully completing her thesis defense.


• May 2023: Received 4.2/5.0 for my teaching of some of the lectures of EE2211 Introduction to Machine Learning. See review quotes here.


• May 2023: Congratulations to Ph.D. students Jingyi Zhao and Jiawei Du for successfully completing their thesis defenses.

Research Interests and Open Positions

Information Theory
Machine Learning
Statistical Signal Processing

I am actively recruiting graduate students in the areas of my research interest above. There are various channels to be admitted to NUS including to the Faculty of Engineering, the Faculty of Science, the Institute of Operations Research and Analytics, the Institute of Data Science, or the Asian Institute of Digital Finance.

There are also multiple positions for talented postdoctoral scholars. Postdoctoral scholars with strong publication records and showing interest in the above research topics are also encouraged to contact me to check with me if there are available positions. Please see this advertisement as well as this.

Selected Recent Publications

1. Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
   Yunlong Hou, Vincent Y. F. Tan, and Zixin Zhong
   Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, Jul 2023 (AR: 1827/6538 ≈ 27.9%)

2. Communication-Constrained Bandits under Additive Gaussian Noise
   Prathamesh Mayekar, Jonathan Scarlett, and Vincent Y. F. Tan
   Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, Jul 2023 (AR: 1827/6538 ≈ 27.9%)

3. Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
   Yujun Shi, Jian Liang, Wenqing Zhang, Vincent Y. F. Tan, and Song Bai
   Proc. of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023 (AR ≈ 31.8%)

4. How Does Pseudo-Labeling Affect the Generalization Error of the Semi-Supervised Gibbs Algorithm?
   Haiyun He, Gholamali Aminian, Yuheng Bu, Miguel R. D. Rodrigues, and Vincent Y. F. Tan
   Proc. of 26th International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, Apr 2023 (AR ≈ 29%)

5. Almost Cost-Free Communication in Federated Best Arm Identification
   Kota Srinivas Reddy, P. N. Karthik, and Vincent Y. F. Tan
   Proc. of the 37th AAAI Conference on Artificial Intelligence (AAAI), Washington DC, USA, Feb 2023 (AR: 1721/8777 ≈ 19.6%)

Oldies But Goldies

1. Information Spectrum Approach to Strong Converse Theorems for Degraded Wiretap Channels
   Vincent Y. F. Tan and Matthieu R. Bloch
   IEEE Transactions on Information Forensics and Security, Vol. 10, No. 9, Pages 1891 - 1904, Sep 2015

2. Asymptotic Estimates in Information Theory with Non-Vanishing Error Probabilities
   Vincent Y. F. Tan
   Foundations and Trends® in Communications and Information Theory, Vol. 11, Nos. 1-2, Pages 1 – 184, 2014

3. Automatic Relevance Determination in Nonnegative Matrix Factorization with the β-Divergence [Slides] [Code]
   Vincent Y. F. Tan and Cédric Févotte
   IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, No. 7, Pages 1592 - 1605, Jul 2013

4. A Large-Deviation Analysis of the Maximum-Likelihood Learning of Markov Tree Structures [Slides]
   Vincent Y. F. Tan, Animashree Anandkumar, Lang Tong and Alan S. Willsky
   IEEE Transactions on Information Theory, Vol. 57, No. 3, Pages 1714 - 1735, Mar 2011

5. Estimating Signals with Finite Rate of Innovation from Noisy Samples: A Stochastic Algorithm [Code]
   Vincent Y. F. Tan and Vivek K Goyal
   IEEE Transactions on Signal Processing, Vol. 56, Issue 10, No. 5135 - 5145, Oct 2008