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.


• Dec 2024: Paper "p-Mean Regret for Stochastic Bandits" accepted to AAAI 2025. Joint work with Anand Krishna, Philips George John, and Adarsh Barik. Here is the paper posted on arXiv.


• Nov 2024: Obtained a Tier 1 grant titled "Adversarially Corrupted Reinforcement Learning with Human Feedback".


• Nov 2024: Invited to be an Area Chair of ICML 2025.


• Nov 2024: Paper Learning Regularized Graphon Mean-Field Games with Unknown Graphons accepted to the Journal of Machine Learning Research. Joint work with Fengzhuo Zhang, Zhaoran Wang, and Zhuoran Yang.


• Nov 2024: Obtained the International Exchanges 2024 Global Round 2 grant with Sharu Theresa Jose of the University of Birmingham.


• Nov 2024: Delivered a plenary lecture at ISITA 2024. Here are my slides.


• Nov 2024: Paper Codes for Correcting Asymmetric Adjacent Transpositions and Deletions accepted to the IEEE Transactions on Communications. Joint work with Shuche Wang and Vu Van Khu.


• Oct 2024: Posted a preprint "Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning". Joint work with Jingyang Li, Jiachun Pan, Kim-Chuan Toh and Pan Zhou.


• Oct 2024: Posted a preprint "On the Convergence of (Stochastic) Gradient Descent for Kolmogorov--Arnold Networks". Joint work with Yihang Gao.


• Oct 2024: Posted a paper "Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits". Joint work with Yunlong Hou and Zixin Zhong. To be presented at NeurIPS 2024.


• Sep 2024: Paper "Stochastic Bandits for Egalitarian Assignment" accepted to the Transactions on Machine Learning Research. Joint work with Eugene Lim and Harold Soh. Here is the version on arXiv.


• Sep 2024: Posted a preprint "Best Arm Identification with Minimal Regret". Joint work with Junwen Yang and Tianyuan Jin.


• Sep 2024: Paper "Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits" accepted to NeurIPS 2024. Joint work with Yunlong Hou and Zixin Zhong.


• Sep 2024: Received the IEEE Transactions on Signal Processing Outstanding Editorial Board Member Award 2024. This is the second time I have received this award.


• Sep 2024: Posted a preprint "A Sample Efficient Alternating Minimization-based Algorithm For Robust Phase Retrieval". Joint work with Adarsh Barik and Anand Krishna.


• Sep 2024: Posted a preprint "A General Framework for Clustering and Distribution Matching with Bandit Feedback". Joint work with postdoc Recep Can Yavas, FYP student Yuqi Huang and collaborator Jonathan Scarlett.


• Sep 2024: We welcome three new research fellows to our group - Le Yang, Gao Yihang and Jin Tianyuan.


• Aug 2024: Invited to the Machine Learning and Statistics: From Theory to Practice workshop at the BIRS-Chennai Mathematical Institute.


• Aug 2024: Posted a preprint "LEARN: An Invex Loss for Outlier Oblivious Robust Online Optimization". Joint work with Adarsh Barik and Anand Krishna.


• Aug 2024: Area Chair of ICLR 2025.


• Aug 2024: Action Editor for Transactions on Machine Learning Research.


• Jul 2024: Paper "Variable-Length Feedback Codes over Known and Unknown Channels with Non-vanishing Error Probabilities" accepted to ITW 2024. Joint work with Recep Can Yavas.


• Jul 2024: Posted a preprint A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent which is joint work with Ph.D. student Shuche Wang. This is the extended version of our ISIT 2024 paper.


• Jul 2024: Invited to serve on the Program Committee of AAAI 2025.


• Jul 2024: Attending ISIT 2024 in Athens, Greece. See you!


• Jun 2024: Paper on Batch Learning via Log-Sum-Exponential Estimator from Logged Bandit Feedback accepted at the ICML 2024 Workshop on Aligning Reinforcement Learning Experimentalists and Theorists. Joint work with Armin Behnamnia, Gholamali Aminian, Alireza Aghaei, Chengchun Shi, and Hamid R. Rabiee.


• Jun 2024: Two recently accepted papers now available on arxiv. (i) Influence Maximization via Graph Neural Bandits with Yuting Feng and Bogdan Cautis and to appear in SIGKDD 2024; (ii) Order-Optimal Instance-Dependent Bounds for Offline Reinforcement Learning with Preference Feedback with Zhirui Chen and to appear at the ICML 2024 Workshop on Models of Human Feedback for AI Alignment.


• Jun 2024: Paper "Order-Optimal Instance-Dependent Bounds for Offline Reinforcement Learning with Preference Feedback" accepted to the ICML 2024 Workshop on Models of Human Feedback for AI Alignment. Joint work with Ph.D. student Zhirui Chen. Preprint can be found above.


• Jun 2024: I will serve on the University Promotion and Tenure Commmittee (UPTC) starting from July 2024.

Research Interests and Open Positions

Online Decision Making, Multi-Armed Bandits, Reinforcement Learning
Information Theory with Applications to 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 Science, the College of Design and Engineering, the Institute of Operations Research and Analytics, and the Integrative Sciences and Engineering Programme (Institute of Data Science).

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. p-Mean Regret for Stochastic Bandits [Full Version on arXiv]
   Anand Krishna, Philips George John, Adarsh Barik, Vincent Y. F. Tan
   Proc. of the 39th AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, PA, Feb 2025 (AR: 3032/12957 ≈ 23.4%)

2. Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
   Yunlong Hou, Vincent Y. F. Tan, and Zixin Zhong
   Proc. of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, Dec 2024 (AR ≈ 25.8%)

3. Learning Regularized Graphon Mean-Field Games with Unknown Graphons
   Fengzhuo Zhang, Vincent Y. F. Tan, Zhaoran Wang, and Zhuoran Yang
   Journal of Machine Learning Research, Nov 2024+

4. Influence Maximization via Graph Neural Bandits [Code] [Video]
   Yuting Feng, Vincent Y. F. Tan, and Bogdan Cautis
   Proc. of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Barcelona, Spain, Aug 2024 (AR ≈ 20%)

5. Optimal Clustering with Bandit Feedback [Slides] [Video]
   Junwen Yang, Zixin Zhong, and Vincent Y. F. Tan
   Journal of Machine Learning Research, Vol. 25, No. 186, Pages 1 - 54, 2024

Selected Older Publications

1. Common Information, Noise Stability, and Their Extensions
   Lei Yu and Vincent Y. F. Tan
   Foundations and Trends® in Communications and Information Theory, Vol. 19, No. 2, Pages 107 - 389, 2022

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