Dr Junqi (Billy) Tang MSc PhD

Dr Junqi Tang

School of Mathematics
Assistant Professor

Contact details

School of Mathematics
Watson Building
University of Birmingham
B15 2TT

Dr Junqi (Billy) Tang is an Assistant Professor in Mathematical Optimisation and Data Science in the School of Mathematics, where he has been based since Spring 2023.

His research interests include large-scale optimisation and learning theory, with applications in data science. Most recently, his research has been focusing on the theoretical foundations of non-convex optimisation in machine learning, data-driven optimisation, and efficient deep unrolling networks in computational imaging.

Personal website.


  • PhD, University of Edinburgh, 2019


Dr Junqi Tang received his MSc and PhD at the University of Edinburgh in 2015 and 2019, respectively. After that he joined the University of Cambridge as a Research Associate in stochastic optimisation and medical imaging. He is appointed as Assistant Professor in mathematical optimisation and data science in Birmingham since March 2023.


Semester 1

LH/LM Non Linear Programming and Heuristic Optimisation


Research Themes

  • Mathematical Optimizstion
  • Machine Learning
  • Learning-to-Optimise/Data-Driven Optimisation
  • Deep Learning for Computational Imaging


Recent publications


Tan, HY, Mukherjee, S, Tang, J & Schönlieb, C-B 2023, 'Data-Driven Mirror Descent with Input-Convex Neural Networks', SIAM Journal on Mathematics of Data Science, vol. 5, no. 2, pp. 558-587. https://doi.org/10.1137/22M1508613

Qian, B, Wen, Z, Tang, J, Yuan, Y, Zomaya, A & Ranjan, R 2022, 'OsmoticGate: Adaptive Edge-based Real-time Video Analytics for the Internet of Things', IEEE Transactions on Computers. https://doi.org/10.1109/TC.2022.3193630

Driggs, D, Tang, J, Liang, J, Davies, M & Schönlieb, C-B 2021, 'A Stochastic Proximal Alternating Minimization for Nonsmooth and Nonconvex Optimization', SIAM Journal on Imaging Sciences, vol. 14, no. 4, pp. 1932-1970. https://doi.org/10.1137/20M1387213

Tang, J, Egiazarian, K, Golbabaee, M & Davies, M 2020, 'The Practicality of Stochastic Optimization in Imaging Inverse Problems', IEEE Transactions on Computational Imaging. https://doi.org/10.1109/TCI.2020.3032101

Conference contribution

Tan, HY, Mukherjee, S, Tang, J, Hauptmann, A & Schönlieb, C-B 2023, Robust Data-Driven Accelerated Mirror Descent. in ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096875

Tachella, J, Tang, J & Davies, M 2021, The Neural Tangent Link Between CNN Denoisers and Non-Local Filters. in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)., 9578172, Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, pp. 8614-8623, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, Tennessee, United States, 20/06/21. https://doi.org/10.1109/CVPR46437.2021.00851

Tang, J, Egiazarian, K & Davies, M 2019, The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/ICASSP.2019.8683368

Tang, J, Golbabaee, M, Bach, F & Davies, M 2018, Rest-Katyusha: Exploiting the Solution’s Structure via Scheduled Restart Schemes. in Advances in Neural Information Processing Systems 31 (NeurIPS 2018). <https://proceedings.neurips.cc/paper_files/paper/2018/file/39059724f73a9969845dfe4146c5660e-Paper.pdf>

Tang, J, Golbabaee, M & Davies, M 2017, Exploiting the structure via sketched gradient algorithms. in 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP). https://doi.org/10.1109/GlobalSIP.2017.8309172

Tang, J, Golbabaee, M & Davies, M 2017, Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares. in Proceedings of the 34th International Conference on Machine Learning. <http://proceedings.mlr.press/v70/tang17a/tang17a.pdf>

View all publications in research portal