Billy Junqi Tang


I am a Research Associate in the University of Edinburgh. I am broadly interested in the fields of statistical machine learning, continuous optimization,  and computational imaging. My research focuses on the design of efficient large-scale optimization algorithms for machine learning, computer vision and signal/image processing applications. I completed my Ph.D in the University of Edinburgh under the supervision of Prof. Mike Davies and the project was fully funded by EU H2020 project MacSeNet Innovative Training Network.

Before starting my research in machine learning and optimization, I had 4 wonderful years in Sichuan University, China as a undergrad majoring in Communication Engineering from 2010 to 2014. Then I undertook a MSc in Signal Processing and Communication at the University of Edinburgh with Prof. Mike Davies from 2014 to 2015, worked on the Non-uniform FFT based 3D image reconstruction algorithms for cone-beam CT. (link)


Recent News:

  • (11/10/2020) Our paper “The Practicality of  Stochastic Optimization in Imaging Inverse Problems” has been accepted for publication in IEEE Transactions on Computational Imaging! (link)


Publications & Preprints

A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse problems

  • Junqi Tang, Mike Davies. 2020
  • [Preprint]

The Neural Tangent Link Between CNN Denoisers and Non-local Filters

  • Julian Tachella, Junqi Tang, Mike Davies. 2020
  • [Preprint]

SPRING: A Fast Stochastic Proximal Alternating Method for Non-smooth Non-convex Optimization

  • Derek Driggs*, Junqi Tang*, Jingwei Liang, Mike Davies, Carola-Bibiane Schönlieb. 2020
  • [Preprint]

The Practicality of Stochastic Optimization in Imaging Inverse Problems

  • Junqi Tang, Karen Egiazarian,  Mohammad Golbabaee, Mike Davies.
  • IEEE Transactions on Computational Imaging, 2020
  • [Download PDF]

The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems

  • Junqi Tang, Karen Egiazarian,  Mike Davies.
  • International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019
  • [Download PDF] [slides]

Rest-Katyusha: Exploiting the Solution’s Structure via Scheduled Restart Schemes

  • Junqi Tang, Mohammad Golbabaee, Francis Bach,  Mike Davies.
  • Advances in Neural Information Processing Systems, 2018.
  • [Download PDF] [Poster]

Exploiting the Structure via Sketched Gradient Algorithms

  • Junqi Tang, Mohammad Golbabaee, Mike Davies.
  • IEEE conference on Signal and Information Processing (GlobalSIP),  2017.
  • [Download PDF]

Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares

  • Junqi Tang, Mohammad Golbabaee, Mike Davies.
  •  International Conference on Machine Learning (ICML), 2017.
  • [Download PDF] [slides]


Reviewer of:

CVPR 2021, ICLR 2021, NeurIPS 2020, NeurIPS 2019

IMA Journal on Numerical Analysis,

Numerical Algorithms,

Mathematics of Operations Research,

IEEE Transactions on Neural Networks and Learning Systems


Junqi Tang

Room 2.12, Alexander Graham Bell Building, Kings Buildings, Edinburgh, UK, EH9 3JL