Skip to menu Skip to content Skip to footer
Dr Nan Ye
Dr

Nan Ye

Email: 
Phone: 
+61 7 334 69095

Overview

Background

Nan Ye's research interest spans machine learning, statistics and optimization. He has published papers on topics including sequential decision making under uncertainty, weakly supervised learning, probabilistic graphical models, statistical learning theory, in venues such as NeurIPS, ICML, ICLR, UAI, JAIR, JMLR. He received an IJCAI-JAIR Best Paper Prize in 2022, and a UAI Best Student Paper Award in 2014.

He is a Lecturer in Statistics and Data Science in the School of Mathematics and Physics in University of Queensland. He previously held postdoc positions at QUT and UC Berkeley from 2015 to 2018, and at NUS from 2013 to 2014. He obtained his PhD in Computer Science from NUS, and completed double first-class honors in Computer Science and Applied Mathematics, also from NUS.

Please visit his personal webpage for more information: https://yenan.github.io/.

Availability

Dr Nan Ye is:
Available for supervision

Research interests

  • machine learning

  • sequential decision making

  • numerical optimization

Works

Search Professor Nan Ye’s works on UQ eSpace

42 works between 2007 and 2024

1 - 20 of 42 works

2024

Journal Article

Structured neural networks for CPUE standardization: A case study of the blue endeavour prawn in Australia's Northern Prawn Fishery

Lei, Yeming, Zhou, Shijie and Ye, Nan (2024). Structured neural networks for CPUE standardization: A case study of the blue endeavour prawn in Australia's Northern Prawn Fishery. Fisheries Research, 279 107140, 107140. doi: 10.1016/j.fishres.2024.107140

Structured neural networks for CPUE standardization: A case study of the blue endeavour prawn in Australia's Northern Prawn Fishery

2024

Journal Article

Eliciting patient preferences and predicting behaviour using Inverse Reinforcement Learning for telehealth use in outpatient clinics

Snoswell, Aaron J., Snoswell, Centaine L. and Ye, Nan (2024). Eliciting patient preferences and predicting behaviour using Inverse Reinforcement Learning for telehealth use in outpatient clinics. Frontiers in Digital Health, 6 1384248. doi: 10.3389/fdgth.2024.1384248

Eliciting patient preferences and predicting behaviour using Inverse Reinforcement Learning for telehealth use in outpatient clinics

2024

Journal Article

Spatial-temporal neural networks for catch rate standardization and fish distribution modeling

Lei, Yeming, Zhou, Shijie and Ye, Nan (2024). Spatial-temporal neural networks for catch rate standardization and fish distribution modeling. Fisheries Research, 278 107097, 107097. doi: 10.1016/j.fishres.2024.107097

Spatial-temporal neural networks for catch rate standardization and fish distribution modeling

2024

Journal Article

Adaptive discretization using Voronoi trees for continuous pOMDPs

Hoerger, Marcus, Kurniawati, Hanna, Kroese, Dirk and Ye, Nan (2024). Adaptive discretization using Voronoi trees for continuous pOMDPs. The International Journal of Robotics Research, 43 (9), 1283-1298. doi: 10.1177/02783649231188984

Adaptive discretization using Voronoi trees for continuous pOMDPs

2024

Conference Publication

Fast controllable diffusion models for undersampled MRI reconstruction

Jiang, Wei, Xiong, Zhuang, Liu, Feng, Ye, Nan and Sun, Hongfu (2024). Fast controllable diffusion models for undersampled MRI reconstruction. 2024 IEEE International Symposium on Biomedical Imaging (ISBI), Athens, Greece, 27-30 May 2024. Piscataway, NJ, United States: IEEE. doi: 10.1109/isbi56570.2024.10635891

Fast controllable diffusion models for undersampled MRI reconstruction

2024

Conference Publication

Robust loss functions for training decision trees with noisy labels

Wilton, Jonathan and Ye, Nan (2024). Robust loss functions for training decision trees with noisy labels. Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, BC, Canada, 20 - 28 February 2024. Washington, DC, United States: Association for the Advancement of Artificial Intelligence. doi: 10.1609/aaai.v38i14.29516

Robust loss functions for training decision trees with noisy labels

2024

Conference Publication

A surprisingly simple continuous-action POMDP solver: lazy cross-entropy search over policy trees

Hoerger, Marcus, Kurniawati, Hanna, Kroese, Dirk and Ye, Nan (2024). A surprisingly simple continuous-action POMDP solver: lazy cross-entropy search over policy trees. 38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence, Vancouver, Canada, 20-27 February 2024. Palo Alto, CA, United States: Association for the Advancement of Artificial Intelligence. doi: 10.1609/aaai.v38i18.29992

A surprisingly simple continuous-action POMDP solver: lazy cross-entropy search over policy trees

2023

Journal Article

Blockwise acceleration of alternating least squares for canonical tensor decomposition

Evans, David and Ye, Nan (2023). Blockwise acceleration of alternating least squares for canonical tensor decomposition. Numerical Linear Algebra with Applications, 30 (6) e2516. doi: 10.1002/nla.2516

Blockwise acceleration of alternating least squares for canonical tensor decomposition

2023

Journal Article

Multi-pass Bayesian estimation: a robust Bayesian method

Lei, Yeming, Zhou, Shijie, Filar, Jerzy and Ye, Nan (2023). Multi-pass Bayesian estimation: a robust Bayesian method. Computational Statistics, 39 (4), 2183-2216. doi: 10.1007/s00180-023-01390-0

Multi-pass Bayesian estimation: a robust Bayesian method

2023

Journal Article

Model‐based offline reinforcement learning for sustainable fishery management

Ju, Jun, Kurniawati, Hanna, Kroese, Dirk and Ye, Nan (2023). Model‐based offline reinforcement learning for sustainable fishery management. Expert Systems, 42 (1) e13324. doi: 10.1111/exsy.13324

Model‐based offline reinforcement learning for sustainable fishery management

2022

Conference Publication

Adaptive Discretization Using Voronoi Trees for Continuous-Action POMDPs

Hoerger, Marcus, Kurniawati, Hanna, Kroese, Dirk and Ye, Nan (2022). Adaptive Discretization Using Voronoi Trees for Continuous-Action POMDPs. Fifteenth Workshop on the Algorithmic Foundations of Robotics WAFR 2022, College Park, MD United States, 22-24 June 2022. Cham, Switzerland: Springer. doi: 10.1007/978-3-031-21090-7_11

Adaptive Discretization Using Voronoi Trees for Continuous-Action POMDPs

2022

Conference Publication

Positive-unlabeled learning using random forests via recursive greedy risk minimization

Wilton, Jonathan, Koay, Abigail M. Y., Ko, Ryan K. L., Miao Xu and Ye, Nan (2022). Positive-unlabeled learning using random forests via recursive greedy risk minimization. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, United States, 29 November - 1 December 2022. New Orleans, LA, United States: Neural information processing systems foundation.

Positive-unlabeled learning using random forests via recursive greedy risk minimization

2021

Conference Publication

MOOR: Model-based offline reinforcement learning for sustainable fishery management

Ju, Jun, Kurniawati, Hanna, Kroese, Dirk and Ye, Nan (2021). MOOR: Model-based offline reinforcement learning for sustainable fishery management. 24th International Congress on Modelling and Simulation, Sydney, NSW, Australia, 5 - 10 December 2021. Sydney, NSW, Australia: International Congress on Modelling and Simulation. doi: 10.36334/modsim.2021.M2.ju

MOOR: Model-based offline reinforcement learning for sustainable fishery management

2021

Conference Publication

Prior versus data: A new Bayesian method for fishery stock assessment

Lei, Y., Zhou, S. and Ye, N. (2021). Prior versus data: A new Bayesian method for fishery stock assessment. 24th International Congress on Modelling and Simulation, Sydney, NSW, Australia, 5 - 10 December 2021. Sydney, NSW, Australia: International Congress on Modelling and Simulation. doi: 10.36334/modsim.2021.A1.lei

Prior versus data: A new Bayesian method for fishery stock assessment

2020

Conference Publication

Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms

Snoswell, Aaron J., Singh, Surya P. N. and Ye, Nan (2020). Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, ACT Australia, 1-4 December 2020. Piscataway, NJ United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/SSCI47803.2020.9308391

Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms

2020

Journal Article

Reading both single and multiple digital video clocks using context-aware pixel periodicity and deep learning

Yu, Xinguo, Song, Wu, Lyu, Xiaopan, He, Bin and Ye, Nan (2020). Reading both single and multiple digital video clocks using context-aware pixel periodicity and deep learning. International Journal of Digital Crime and Forensics, 12 (2), 21-39. doi: 10.4018/IJDCF.2020040102

Reading both single and multiple digital video clocks using context-aware pixel periodicity and deep learning

2020

Conference Publication

Discriminative particle filter reinforcement learning for complex partial observations

Ma, Xiao, Karkus, Peter, Hsu, David, Lee, Wee Sun and Ye, Nan (2020). Discriminative particle filter reinforcement learning for complex partial observations. ICLR 2020: Eighth International Conference on Learning Representations, Virtual, 26 April - 1 May 2020. International Conference on Learning Representations, ICLR.

Discriminative particle filter reinforcement learning for complex partial observations

2020

Conference Publication

Greedy convex ensemble

Nguyen, Thanh Tan, Ye, Nan and Bartlett, Peter (2020). Greedy convex ensemble. Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), Online, 7-15 January 2021. Palo Alto, CA United States: A A A I Press. doi: 10.24963/ijcai.2020/429

Greedy convex ensemble

2020

Journal Article

Nesterov acceleration of alternating least squares for canonical tensor decomposition: Momentum step size selection and restart mechanisms

Mitchell, Drew, Ye, Nan and De Sterck, Hans (2020). Nesterov acceleration of alternating least squares for canonical tensor decomposition: Momentum step size selection and restart mechanisms. Numerical Linear Algebra with Applications, 27 (4) e2297. doi: 10.1002/nla.2297

Nesterov acceleration of alternating least squares for canonical tensor decomposition: Momentum step size selection and restart mechanisms

2019

Conference Publication

Maximum entropy approaches for inverse reinforcement learning

Snoswell, A. J., Singh, S. P. N. and Ye, N. (2019). Maximum entropy approaches for inverse reinforcement learning. INFORMS-APS, Brisbane, Australia, 3-5 July 2019.

Maximum entropy approaches for inverse reinforcement learning

Funding

Current funding

  • 2023 - 2027
    Analytics for the Australian Grains Industry (AAGI)
    Grains Research & Development Corporation
    Open grant
  • 2021 - 2024
    Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries
    ARC Discovery Projects
    Open grant

Past funding

  • 2019 - 2021
    Modelling environmental changes and effects on wild-caught species in Queensland
    Fisheries Research & Development Corporation
    Open grant
  • 2019 - 2020
    Sparse Methods for Learning, Prediction and Decision Making
    UQ Early Career Researcher
    Open grant

Supervision

Availability

Dr Nan Ye is:
Available for supervision

Before you email them, read our advice on how to contact a supervisor.

Supervision history

Current supervision

  • Doctor Philosophy

    Reinforcement Learning for Large and Complex Partially Observable Markov Decision Processes

    Principal Advisor

    Other advisors: Professor Dirk Kroese

  • Doctor Philosophy

    Efficient graph representation learning with neural networks and self-supervised learning

    Principal Advisor

    Other advisors: Professor Fred Roosta

  • Doctor Philosophy

    Data-driven framework for Sequential Decision Making in Operations Research

    Principal Advisor

  • Doctor Philosophy

    Machine Learning for Cyber Security

    Principal Advisor

    Other advisors: Dr Miao Xu

  • Doctor Philosophy

    Reinforcement Learning for Partially Observable Environments

    Principal Advisor

    Other advisors: Professor Dirk Kroese

  • Doctor Philosophy

    Machine Learning for Quantitative Fisheries Stock Assessments

    Principal Advisor

    Other advisors: Emeritus Professor Jerzy Filar

  • Doctor Philosophy

    High-stakes Decision Making with Weakly Supervised Data

    Associate Advisor

    Other advisors: Dr Miao Xu

  • Doctor Philosophy

    High-stakes Decision Making with Weakly Supervised Data

    Associate Advisor

    Other advisors: Dr Miao Xu

  • Doctor Philosophy

    AI/ML Framework for Mixed-integer Nonlinear Optimisation

    Associate Advisor

    Other advisors: Professor Fred Roosta

  • Doctor Philosophy

    Development of novel deep learning methods for medical imaging

    Associate Advisor

    Other advisors: Professor Feng Liu, Dr Hongfu Sun

  • Doctor Philosophy

    Breast cancer metastasis prediction via machine learning and spatial cellular pathology

    Associate Advisor

    Other advisors: Dr Quan Nguyen

Completed supervision

Media

Enquiries

For media enquiries about Dr Nan Ye's areas of expertise, story ideas and help finding experts, contact our Media team:

communications@uq.edu.au