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

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.


• Jun 2025: Appointed Area Editor of Shannon Theory and Information Measures of the IEEE Transactions on Information Theory.


• Jun 2025: Posted a paper on the arxiv: "Finite-Time Information-Theoretic Bounds in Queueing Control". Joint work with Yujie Liu and Yunbei Xu.


• Jun 2025: Paper "Enhancing Multi-Text Long Video Generation Consistency without Tuning: Time-Frequency Analysis, Prompt Alignment, and Theory" accepted as a best paper to the Building Physically Plausible World Models (WM) workshop at ICML 2025.


• Jun 2025: Posted a paper on the arxiv: "Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning". To be presented as a spotlight poster at ICML 2025.


• Jun 2025: Posted a paper on the arxiv: "Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget". Joint work with Ph.D. student Jie Bian. To be presented at UAI 2025.


• Jun 2025: Rated 4.7/5.0 for my teaching of EE5137 Stochastic Processes last semester. See some review quotes here.


• Jun 2025: Congrats to PhD student Fengzhuo Zhang for successfully defending his excellent thesis.


• May 2025: Posted a paper on the arxiv: "Best Arm Identification with Possibly Biased Offline Data". Joint work with Le Yang and Wang Chi Cheung. To be presented at UAI 2025.


• May 2025: Posted a paper on the arxiv: "BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms". To be presented at ICML 2025.


• May 2025: Congrats to former PhD student Haiyun He for accepting a position as an Assistant Professor in the IoT Thurst at HKUST Guangzhou!


• May 2025: Congrats to Research Fellow Adarsh Barik for accepting a position as an Assistant Professor in the Computer Science and Engineering (CSE) department at IIT Delhi!


• May 2025: Two papers accepted to UAI 2025: "Best Arm Identification with Possibly Biased Offline Data" (with Le Yang and Wang Chi Cheung) and "Asymptotically Optimal Linear Best Feasible Arm Identification with Fixed Budget" (with PhD student Jie Bian). See CS Conference Papers for details.


• May 2025: Three papers accepted to ICML 2025: "LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos", "BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms" and "Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning" (spotlight). See CS Conference Papers for details.


• Apr 2025: Papers "A General Framework for Clustering and Distribution Matching With Bandit Feedback" (joint work with Recep Can Yavas, Yuqi Huang and Jonathan Scarlett) and "Ensemble-Tight Second-Order Asymptotics for Guessing-Based Decoding With Abandonment" (joint work with Hamdi Joudeh) accepted to ISIT 2025. See you in Ann Arbor, Michigan.


• Mar 2025: Congrats to Yujun Shi for successfully defending his excellent Ph.D. thesis.


• Mar 2025: Posted a preprint Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework. Here is the project page.


• Mar 2025: Delivered a plenary talk at NCC 2025. Here are my slides.


• Mar 2025: Congrats to Junwen Yang and Zhirui Chen for successfully defending their excellent Ph.D. theses.


• Feb 2025: Invited to serve as a Senior Area Chair for NeurIPS 2025.


• Feb 2025: Paper Variable-Length Feedback Codes over Known and Unknown Channels with Non-vanishing Error Probabilities accepted to the IEEE Transactions on Information Theory! Joint work with Recep Can Yavas.


• Feb 2025: Posted a preprint "Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networks". Joint work with Yihang Gao and Michael Ng.


• Feb 2025: Posted a preprint "Ensemble-Tight Second-Order Asymptotics and Exponents for Guessing-Based Decoding with Abandonment". Joint work with Hamdi Joudeh (Eindhoven University of Technology).


• Feb 2025: Paper A Mirror Descent-Based Algorithm for Corruption-Tolerant Distributed Gradient Descent accepted to the IEEE Transactions on Signal Processing. Congrats to Ph.D. student Shuche Wang.


• Jan 2025: Invited to be a plenary speaker at the 2025 National Conference on Communications at IIT Delhi.


• Jan 2025: Paper "Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning" accepted to ICLR 2025 in Singapore! Joint work with Jingyang Li, Jiachun Pan, Kim-Chuan Toh, and Pan Zhou. Selected as an oral presentation (top 1.8%).


• Jan 2025: Paper "Optimal Multi-Objective Best Arm Identification with Fixed Confidence" accepted to AISTATS 2025 in Phuket, Thailand! Joint work with Zhirui Chen, P. N. Karthik and Yeow Meng Chee.


• Jan 2025: Paper A General Framework for Clustering and Distribution Matching with Bandit Feedback accepted by the IEEE Transactions on Information Theory! Joint work with Recep Can Yavas, Yuqi Huang, and Jonathan Scarlett.

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. Optimal Multi-Objective Best Arm Identification with Fixed Confidence
   Zhirui Chen, P. N. Karthik, Yeow Meng Chee, and Vincent Y. F. Tan
   Proc. of 26th International Conference on Artificial Intelligence and Statistics (AISTATS), Phuket, Thailand, May 2025 (AR ≈ 31.3%)

2. 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%)

3. 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%)

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