Contact
School of Mathematics, Statistics and Actuarial Science,
University of Essex,
Colchester, CO4 3SQ
If you are interested in researching on Probability/Statistics/Mathematics for Information Theory or Machine Learning, please don't hesitate to contact me. Information for Ph.D. applicants to the University of Essex is available at https://www.essex.ac.uk/postgraduate/research/applying-to-essex.
Brief Bio.
Lan V. Truong (Senior Member, IEEE) was born in Quang Binh province, Vietnam, where he studied at Vo Nguyen Giap Gifted High School from 1995 to 1998. He received the B.S.E. degree in electronics and telecommunications from the Posts and Telecommunications Institute of Technology (PTIT), Hanoi, Vietnam, in 2003, and the M.S.E. degree from the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA, in 2011, and the Ph.D. degree from the Department of Electrical and Computer Engineering, National University of Singapore (NUS), Singapore, in 2018. He was an Operation and Maintenance Engineer with MobiFone Telecommunications Corporation, Hanoi, for several years. He spent one year as a Research Assistant with the NSF Center for Science of Information and the Department of Computer Science, Purdue University, in 2012. From 2013 to 2015, he was a University Lecturer with the Department of Information Technology Specialization, FPT University, Hanoi, Vietnam. From 2018 to 2019, he was a Research Fellow with the Department of Computer Science, School of Computing, NUS. From 2020 to 2023, he was a Research Associate with the Department of Engineering, University of Cambridge, U.K. He is currently a Lecturer (Assistant Professor) at the School of Mathematics, Statistics and Actuarial Science, University of Essex, U.K. His research interests include high-dimensional statistics, deep learning theory, statistical learning, and information theory. Major research topics of interest include:
Mathematical Foundations of Deep Learning and Large Language Models. Sample works: "On Rademacher Complexity-based Generalisation Bounds for Deep Learning", "Generalization Error Bounds on Deep Learning with Markov Datasets", "Global Convergence Rate of Deep Equilibrium Models with General Activations", "On Rank-Dependent Generalisation Error Bounds for Transformers".
Information Theory for Communications, Deep Learning, and Large Language Models. Sample works: "On Gaussian MACs With Variable-Length Feedback and Non-Vanishing Error Probabilities", "Moderate Deviations Asymptotics for Variable-Length Codes with Feedback", "Concentration Properties of Random Codes".
Kernel Methods for Machine Learning and Deep Learning. Sample works: "Generalisation Bounds on Multiple-Kernel Learning with Mixed Datasets".
High-Dimensional Statistics and Algorithms. Sample works: "Fundamental limits and algorithms for sparse linear regression with sublinear sparsity", "Replica Analysis of the Linear Model with Markov or Hidden Markov Signal Priors", "Support Recovery in the Phase Retrieval Model: Information-Theoretic Fundamental Limits".
Recent News
Paper "Global Convergence Rate of Deep Equilibrium Models with General Activations" was accepted to Transactions on Machine Learning Research (TMLR).
Invited to serve on the Technical Program Committee of The IEEE International Symposium on Information Theory (ISIT 2025)
Paper "On Rank-Dependent Generalisation Error Bounds for Transformers" was uploaded to Arxiv.
Invited to serve on the Program Committee of The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)
My recent work shows that the Rademacher complexity approach can lead to tight generalization bounds on CNNs for Binary Image Classifications. Check the latest version on Arxiv:
"On Rademacher Complexity-based Generalisation Bounds for Deep Learning".
Our paper "Generalized Random Gilbert-Vashamov Codes: Typical Error Exponents and Concentration Properties" was published in IEEE Transactions on Information Theory, Feb. 2024.
Our paper "Concentration Properties of Random Codes" was published in IEEE Transactions on Information Theory, Dec. 2023.
Paper "Replica Analysis of the Linear Model with Markov or Hidden Markov Signal Priors" was published in IEEE Transactions on Information Theory, Dec. 2023.
I joined the School of Mathematics, Statistics and Actuarial Science at the University of Essex as a Lecturer (Assistant Professor) in Sept. 2023.
Paper "Fundamental limits and algorithms for sparse linear regression with sublinear sparsity" was published in the Journal of Machine Learning Research (JMLR), Apr. 2023.
Paper "Generalization Error Bounds on Deep Learning with Markov Datasets" was published in the Proc. of The Thirty-Sixth Annual Conference on Neural Information Processing Systems (NeurIPS), Dec. 2022.
Paper "On Linear Models with Markov Signal Priors" was published in the Proc. of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), Mar. 2022.
Our paper "On the All-Or-Nothing Behavior of Bernoulli Group Testing" was published in IEEE Journal on Selected Areas In information Theory (Special Issue On Estimation and Inference), Jan. 2021.
[Google Scholar] [DBLP] [ResearchGate]