Dr Vu Nguyen

I am a machine learning researcher at Amazon Research Australia in Anton's team. Prior to this appointment, I was a Senior Research Associate in Machine Learning at University of Oxford, working with Prof. Mike Osborne in Machine Learning Research Group and Prof. Andrew Briggs. I am an associate member of Oxford-Man Institute of Quantitative Finance. Before that, I was a Research Scientist at Credit AI - Trusting Social and an Associate Research Fellow at PRADA, Deakin University with ARC Laureate Prof Svetha Venkatesh. I obtained my PhD at Deakin University where I am very fortunate to be advised by Prof. Dinh Phung and Prof. Svetha Venkatesh in Dec 2015.

Research Interests

Bayesian Optimization, Gaussian Process, Deep Reinforcement Learning
Bayesian Nonparametric, Multilevel Modelling

Awards

Postdoc-NeT-AI Fellows, DAAD, Germany, Oct 2020
Google Cloud Platform Education Grant, Aug 2020
Travel Grant EEML on Deep Learning and Reinforcement Learning, Romania July 2019
Vice Chancellor Award for Outstanding Contribution, Deakin University 2017
Selected as Best Papers for KAIS - ICDM 2017
Best Poster Award - ICME 2017, 4th World Congress on Integrated Computational Materials Engineering 2017
Best Paper Runner up Award and Best Poster Award - ACML 2016
Heidelberg Laurate Forum 2015, Top 200 young scientist around the world to interact with the Laurates in Germany
First Prize in Student Research Competition 2011, University of Science, Vietnam National University HCM
Travel Grant Machine Learning Summer School, Singapore, 2011.

Recent News

July 2021 Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning has been selected as a Spotlight presentation at UAI 2021.
Jun 2021 Our multi-disciplinary work in automating the measurement of quantum devices using DRL has been accepted at Nature NPJ Quantum Information.
May 2021 Our paper entitled Simulation-based Optimisation to Quantify Heterogeneity of Specific Ventilation and Perfusion in the Lung by the Inspired Sinewave Test has been accepted at Scientific Reports. This is the applied research paper using Bayesian optimisation for studying ventilation and perfusion in human lung.
May 2021 Our paper entitled Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning has been accepted at UAI 2021 ! Big congratulations to Sam.
May 2021 We got two papers accepted at ICML2021 ! Congratulations to all collaborators. Click here for details.
Apr 2021 I gave a talk "Bayesian Black-box Optimization" at the ECMS, University of Adelaide
Feb 2021 We release a preprint paper addressing the problem of mixed optimization between continuous and categorical variables in high-dimensional space.
Jan 2021 The email vu@robots.ox.ac.uk has expired, please use vu@ieee.org for contacting me. Thanks!.
Jan 2021 Our applied science paper using machine learning and Bayesian optimization for neuron-stimulation has been accepted. This is a collaborated work with experimental psychology scientists.
Dec 2020 I have joined Amazon Research Australia to continue working on cutting edge research for industrial scale.
Dec 2020 Attending and presenting our works at NeurIPS2020 .
Nov 2020 Our Population-based Bandit (PB2) has been included into Ray Tune! Check out the blog post.
Nov 2020 I am giving a tutorial on Bayesian optimization at ACML2020.
Oct 2020 I am selected as a Postdoc-NeT-AI Fellow, DAAD, Germany 2021 (acceptance rate 22/196).
Sep 2020 Three of our papers have been fortunately accepted at NeurIPS2020! Congratulations and thank you to all my fantastic collaborators Vaden Masrani, Rob Brekelmans, Mike Osborne , Frank Wood, Jack Parker-Holder, Stephen Roberts, among many others !
Sep 2020 Our recent work using ML for quantum device fine-tuning has been accepted to New Journal of Physics. Congratulations Nina!
Aug 2020 I am awarded the Google Cloud Platform Education Grant 2020-2021 for accelerating my current research in AutoML.
Jul 2020 Our paper Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits has been selected at Top 3% for the Contributed Talk at AutoML workshop at ICML2020. Congratulations Jack !!!
Jun 2020 Our papers Bayesian Optimization for Iterative Learning and Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits have been accepted at AutoML workshop at ICML2020.
Jun 2020 Our papers have been accepted at ICML2020. Congratulations to all collaborators. Knowing The What But Not The Where in Bayesian Optimization and Bayesian Optimisation over Multiple Continuous and Categorical Inputs .
Feb 2020 Excited to share our recent papers on Bayes Continual Learning and One-shot Bayes Opt.
Jan 2020 I am giving a tutorial in Gaussian Process and Bayesian Optimisation at Quinhon University.
Dec 2019 I am giving a talk on Knowing the what, but not the where in Bayesian Optimization at VinAI Research.
Dec 2019 I am attending NeurIPS 2019.
Nov 2019 I am invited to review for ICML 2020.
Oct 2019 I am excited to teach this year Data Estimation and Inference course CDT AIMS.
Oct 2019 Our paper on Controlling Quantum Device Measurement using Deep Reinforcement Learning has been accepted at Deep Reinforcement Learning workshop at NeurIPS 2019 .
Oct 2019 Congratulations to Sam for his paper being accepted at Bayesian Deep Learning workshop at NeurIPS 2019 .
Aug 2019 I am visiting Australia this month. I am giving talks at University of Melbourne, Monash University and RMIT University.
Aug 2019 Our paper entitled Efficient Bayesian Optimization for Uncertainty Reduction over Perceived Optima Locations has been accepted at ICDM 2019.
Jul 2019 I will serve as a reviewer for ICLR 2020.
Jul 2019 I am attending EEML2019. Looking forward to meeting you all.
Jun 2019 I am awarded the Young Investigator Training Program grant to visit Italian university link
May 2019 I am giving an invited talk at Oxford Aging Institute link
May 2019 Check out our recent work with Mike in exploiting the known optimum value for Bayesian optimization arxiv. In many situations in blackbox optimization and hyper-parameter optimization, we observe the optimum output in advance and the goal is to find the optimum input.
Apr 2019 I am excited to be the recipient of the travel grant to attend EEML on Deep Learning and Reinforcement Learning, Bucharest in July 2019
Feb 2019 I am awarded the NVIDIA GPU grant. Many thanks to NVIDIA for their support.
Jan 2019 I am joining University of Oxford to work on a machine learning for quantum technologies project with Prof. Mike Osborne and Prof. Andrew Briggs
Dec 2018 I will serve as the PC for IJCAI 2019
Oct 2018 I have recently joined Credit AI - Trusting Social (for a 3 months contract) as a Research Scientist working on deep reinforcement learning for finance technology
Sep 2018 Our paper Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation has been accepted at NIPS 2018. Congratulations Shiva
Aug 2018 Our paper Accelerating Experimental Design by Incorporating Experimenter Hunches has been accepted at ICDM 2018. Congratulations Cheng
June 2018 Our paper Exploration Enhanced Expected Improvement for Bayesian Optimization has been accepted at ECML 2018. Congratulations Julian
May 2018 Invited to serve as a reviewer for PloS ONE
Dec 2017 Awarded Vice Chancellor Award for Outstanding Contribution with our team
Nov 2017 Attended IEEE ICDM 2017 New Orleans, USA to present the paper entitled Weakly Specified Search Space in Bayesian optimization
Nov 2017 Attended ACML 2017 Seoul, Korea to present the paper entitled Regret for Expected Improvement under Stopping Condition
Aug 2017 Attended IJCAI 2017 Melbourne, Australia to present the paper entitled Discriminative Bayesian Nonparametric Clustering
Dec 2016 Attended NIPS 2016 Workshop on Bayesian Optimization Barcelona, Spain to present our posters.
Dec 2016 Attended IEEE ICDM 2016 Barcelona, Spain to present the paper entitled Budgeted Batch Bayesian Optimization and One-Pass Logistic Regression
Dec 2016 Attended ICPR 2016 Cancun, Mexico to present multiple papers.
Nov 2016 Awarded Best Paper (Runner up) and Best Poster Award for a single paper A Bayesian Nonparametric Approach for Multi-label Classification .
Nov 2016 Attended ACML 2016 Hamilton, Newzeland to present the paper entitled A Bayesian Nonparametric Approach for Multi-label Classification .

Web Counter