Quan M. Nguyen
Machine Learning Theory Researcher
Email: manhquan233@gmail.com
CV (updated March 2026): Link
Embedded Files
About me
About me
I am an AI Researcher at A5 Labs, an AI-for-gaming startup based in California. My job at A5 focuses on building resource-efficient training algorithms for large-scale deep reinforcement learning systems that solve imperfect-information games.
In general, I have broad interests in machine learning and optimization theory as well as their practical applications. My current research focuses on two main areas:
Understanding the training dynamics and generalization guarantees for deep and shallow neural networks, particularly transformers and two-layer neural nets.
Developing theoretical guarantees for online and non-convex optimization, especially on problems arising from training deep and shallow models.
Additionally, I am recently interested in the mathematics of imperfect-information games like Poker.
Previously, I have worked on adaptive regret bounds for adversarial multi-armed bandits, stochastic optimization and online reinforcement learning.
I completed my PhD study in machine learning theory at University of Victoria (Canada), advised by Nishant Mehta. Before that, I worked as a research scientist at University of Hamburg (Germany) after having obtained a Masters in Intelligence Adaptive Systems there, advised by Mikko Lauri and Simone Frintrop. Prior to Hamburg, I did a Bachelor in Engineering from FPT University (Vietnam), supervised by Phan Duy Hung and Lan V. Truong, and then worked full-time as a software developer for a few years.
How to pronounce my name: I go by "Quan", which can be pronounced like |Kwan|.
Recent News
Recent News
March 30, 2026: I will give an invited talk on my ALT 2026 paper at the Dartmouth/Berkeley/Rice Reading Group on Foundation Models/AI.
Feb 22-28, 2026: I attended ALT 2026 at the Fields Institute in Toronto. It was a blast! I had a lot of fun talking to Matus, anh Thang (Grenoble), Trung Kuroni, and everyone else. I also bought a mug with the Fields institute logo on it! At ALT, I gave two talks: one filling-in talk for Hamish on sparse non-parametric bandits, and one talk on my own paper on tuning Adam's momentum factors. The first talk went super well without hiccups. However, the second talk didn't go as well as I expected due to a weird allegic reaction that made me unable to speak for the first minute. The rest of that talk went smoothly though.
Jan 15, 2026: I successfully defended my PhD thesis.
Dec 2025 (2): one single-author paper accepted to ALT.
Dec 2025 (1): I joined A5Labs / AceGuardian (a California startup) as an AI Researcher (remote).
Nov 2025: my PhD defense is scheduled on January 15th, 2026.
Oct 2025: new paper "How to Set β1, β2 in Adam: An Online Learning Perspective" uploaded to Arxiv.
Sep 2025: I visited Christos's group at UBC and gave a talk on the expressive power of one-layer transformers for in-context recall task. It was a great experience discussing research with Christos, Tina and Puneesh.
Jul 2025: I attended COLT in Lyon and ICML in Vancouver. I gave a talk at COLT on adaptive regret bounds for multi-armed bandits, and gave a poster presentation at ICML on stochastic min-max optimization. It was great visiting ENS, catching up with familiar folks (Taira, Shinji, Cristóbal, Bingshan, Andi, Waleed....) and meeting new (Yan, Haipeng, Yuwei, Mark, Christos....) people!
May 2025 (2): new paper "One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks" uploaded to Arxiv. This is a joint work with Thanh Nguyen-Tang.
May 2025 (1): One paper accepted to ICML and another paper accepted to COLT.
Feb 2025: new paper "Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching." uploaded to Arxiv. This is a joint work with Shinji Ito, Junpei Komiyama and Nishant Mehta. This work came out of my time at RIKEN AIP.
Jan 2025: I officially became a Canadian permanent resident!
Nov 2024: I got selected as a Top Reviewer at NeurIPS 2024 and received a free registration pass. Thank you NeurIPS, and see you all in Vancouver this December!
Oct 2024: new paper "Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity" uploaded to Arxiv. This is a joint work with Nishant Mehta and Cristóbal Guzmán.
Sep 2024: I started my PhD Internship at RIKEN AIP / University of Tokyo in Japan, hosted by Shinji Ito. Excited to spend the next three months working on multi-armed bandits in Todai.
May 2024: I attended AISTATS 2024 in Valencia, Spain and met my Hamburg classmate and close friend Waleed Mustafa there. Also, it was great talking to Nicolo Cesa-Bianchi when he visited my poster!
Mar 2024: I attended AAAI 2024 in Vancouver and gave a workshop talk on group distributionally robust optimization.
Jan 2024: One paper accepted to AISTATS.
Jul 2023: Passed PhD Candidacy.
Feb 2023: I attended ALT at NUS in Singapore. This was my first time Singapore. Love the food and the NUS campus!
Dec 2022: One paper accepted to ALT. This is my first pure-theory paper.
Preprints / Submitted
Preprints / Submitted
[1] Quan Nguyen, Thanh Nguyen-Tang. One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks. 2025.
Peer-Reviewed Publications
Peer-Reviewed Publications
[9] Quan Nguyen. How to Set β1, β2 in Adam: An Online Learning Perspective. International Conference on Algorithmic Learning Theory (ALT) 2026.
[8] Quan Nguyen, Shinji Ito, Junpei Komiyama, Nishant A. Mehta. Data-dependent Bounds with T-Optimal Best-of-Both-Worlds Guarantees in Multi-Armed Bandits using Stability-Penalty Matching. Conference on Learning Theory (COLT) 2025.
[7] Quan Nguyen, Nishant A. Mehta, Cristóbal Guzmán. Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity. International Conference on Machine Learning (ICML) 2025. A short version was accepted to AAAI 2024 Workshop on Biased and Scared Data.
[6] Quan Nguyen, Nishant A. Mehta. Near-optimal Per-Action Regret Bounds for Sleeping Bandits. International Conference on Artificial Intelligence and Statistics (AISTATS) 2024. Arxiv.
[5] Quan Nguyen, Nishant A. Mehta. Adversarial Online Multi-Task Reinforcement Learning. International Conference on Algorithmic Learning Theory (ALT) 2023. Long version.
[4] Quan Nguyen, Julius Richter, Mikko Lauri, Timo Gerkmann, Simone Frintrop. Improving mix-and-separate training in audio-visual sound source separation with an object prior. International Conference on Pattern Recognition (ICPR) 2020. (Oral Presentation, top 4%). PDF.
[3] Quan Nguyen, Mikko Lauri, Simone Frintrop. Distance dependent Maximum margin Dirichlet Process Mixture. The 16th Pacific Rim International Conferences on Artificial Intelligence (PRICAI), 2019
[2] N. Churamani, P. Anton, M. Bruegger, E. Fliesswasser, T. Hummel, J. Mayer, W. Mustafa, H. G. Ng, T. Nguyen, Q. Nguyen, M. Soll, S. Springenberg, S. Griffiths, S. Heinrich, N. Navarro-Guerrero, E. Strahl, J. Twiefel, C. Weber, S. Wermter. (2017). The Impact of Personalisation on Human-Robot Interaction in Learning Scenarios. Proceedings of the Fifth International Conference on Human Agent Interaction (HAI), pages 171–180. PDF.
[1] H. G. Ng, P. Anton, M.Bruegger, N. Churamani, E. Fliesswasser, T. Hummel, J. Mayer, W. Mustafa, T. Nguyen, Q. Nguyen, M. Soll, S. Springenberg, S. Griffiths, S. Heinrich, N. Navarro-Guerrero, E. Strahl, J. Twiefel, C. Weber, S. Wermter. (2017). Hey Robot, Why Don’t You Talk To Me?. Proceedings of the IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pages 728–731.
Talks and Conference Presentation
Talks and Conference Presentation
How to Set β1, β2 in Adam: An Online Learning Perspective.
International Conference on Algorithmic Learning Theory (ALT), Toronto, February 2026.
Dartmouth/Berkeley/Rice Reading Group on Foundation Models/AI, March 2026.
One-layer transformers for In-context recall tasks: Bayes Optimality and Out-of-distribution Generalization. Invited Talk. University of British Columbia, Vancouver, September 2025.
Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity.
AAAI Workshop on Artificial Intelligence with Biased or Scarce Data, Vancouver, March 2024.
ICML Poster, July 2025.
Data-dependent Bounds with Best-of-both-world Guarantees for Multi-armed Bandits using Stability-Penalty Matching.
RIKEN Sequential Decision Making Seminar, Tokyo, November 2024.
COLT oral presentation, July 2025
Adversarial Online Multi-Task Reinforcement Learning. International Conference on Algorithmic Learning Theory (ALT), Singapore, February 2023.
Improving mix-and-separate training in audio-visual sound source separation with an object prior. International Conference on Pattern Recognition (ICPR), Milan, Italy, 2020.
Distance dependent Maximum margin Dirichlet Process Mixture. The 16th Pacific Rim International Conferences on Artificial Intelligence (PRICAI), Fiji, 2019.
Non-parametric Bayesian clustering with applications in object candidate detection. Machine Learning Oberseminar, University of Hamburg, Germany, 2017.
Services
Services
PC member for ECAI (2025)
Reviewer for NeurIPS (2023 - 2025), ICML (2025-), ICLR (2024, 2025), AISTATS (2025), ICRA (2018), CVPR (2018), TMLR (2025), Artificial Intelligence Journal (2026)
Teaching and Mentoring
Teaching and Mentoring
Teaching Assistant for CSC 531/ CSC 431 Machine Learning Theory, University of Victoria. Fall 2024.
Teaching Assistant for CSC 503 / SENG 474 Data Mining. University of Victoria. Spring 2022, Spring 2023, Fall 2024, Summer 2025.
Teaching Assistant for Cognitive Computer Vision. University of Hamburg. 2018 and 2019.
Mentoring:
Irene Hang Duong (BSc CS at UVic. Now a software engineer at Amazon Google).
Honours and Awards
Honours and Awards
NeurIPS's Top Reviewer, 2024.
Charles S. Humphrey Graduate Student Awards, University of Victoria, 2023.
University of Victoria Conference Travel Awards, 2023.
University of Victoria Graduate Awards for Top-Performing PhD Students. 2021 - 2023.
University of Victoria Graduate Fellowship Awards. 2021-2024.
Instagram Machine Learning Competition. Second Prize. 2017.
Vietnam ACM ICPC National Algorithm Programming Competition. Bronze prize. 2013.
Full scholarships for Undergraduate study in Software Engineering, FPT University. 2009-2014.
Odon Vallet scholarship for exceptional Vietnamese high school students. 2009.
Vietnam High School National Physics Contest. Third prize. 2009.
Vietnam National Mathematics And Youth Magazine Annual Contest. Second Prize. 2008.
Vietnam National Physics And Youth Magazine Annual Contest. First Prize. 2008.
Miscellaneous
Miscellaneous
I enjoy solving competitive mathematics and programming puzzles. I am active on LeetCode, and also enjoy solving problems on TopCoder.
Badminton is one of my biggest hobbies. I am a big fan of Taufik Hidayat and Tai Tzu Ying and often practice their signature shots (in particular, backhand smash and reverse slices). Also, I have been a member of UVic's Badminton Club since 2021.
I also watch Xiangqi (Chinese chess) videos from time to time. I particularly enjoy the matches played by Hu Rong Hua and Li Laiqun. Sometimes I watch Western chess videos as well.
Page updated
Google Sites
Report abuse