Billy Junqi Tang

billy_sow

Hi! I am a Research Associate with the University of Edinburgh. My current research interests include statistical machine learning, explainable AI, large-scale optimization, with applications in computer vision and image processing.

In 2019, 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. Prior to that, I had 4 wonderful years in Sichuan University, China as a undergrad majoring in Communication Engineering from 2010 to 2014.

***********************************************************************************

Recent News:

  • (3/3/2021) Our paper “The Neural Tangent Link Between CNN Denoisers and Non-Local Filters” has been accepted by CVPR 2021 (Oral presentation) !
  • (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

In preparation / Under review:

  1. Derek Driggs*, Junqi Tang*, Jingwei Liang, Mike Davies, Carola-Bibiane Schönlieb. SPRING: A Fast Stochastic Proximal Alternating Method for Non-smooth Non-convex Optimization.  2021 [Preprint]
  2. Junqi Tang, Mike Davies.  A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems. 2021 [Preprint]
  3. Bin Qian, Zhenyu Wen, Junqi Tang, Ye Yuan, Albert Zomaya, Rajiv Ranjan. OsmoticGate: Adaptive Edge-based Real-time Video Analytics for the Internet of Things.  2021 [Preprint]

Publications:

  1. Julian Tachella, Junqi Tang, Mike Davies. The Neural Tangent Link Between CNN Denoisers and Non-local Filters.  Computer Vision and Pattern Recognition (CVPR), 2021 (to appear) [link]
  2. Junqi Tang, Karen Egiazarian,  Mohammad Golbabaee, Mike Davies. The Practicality of Stochastic Optimization in Imaging Inverse Problems. IEEE Transactions on Computational Imaging, 2020 [Download PDF]
  3. Junqi Tang, Karen Egiazarian,  Mike Davies. The Limitation and Practical Acceleration of Stochastic Gradient Algorithms in Inverse Problems. International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019 [Download PDF] [slides]
  4. Junqi Tang, Mohammad Golbabaee, Francis Bach,  Mike Davies. Rest-Katyusha: Exploiting the Solution’s Structure via Scheduled Restart Schemes. Advances in Neural Information Processing Systems (NeurIPS), 2018.[Download PDF] [Poster]
  5. Junqi Tang, Mohammad Golbabaee, Mike Davies. Exploiting the Structure via Sketched Gradient Algorithms. IEEE conference on Signal and Information Processing (GlobalSIP), 2017.[Download PDF]
  6. Junqi Tang, Mohammad Golbabaee, Mike Davies. Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares. International Conference on Machine Learning (ICML), 2017.[Download PDF] [slides]

Thesis:

  1. Randomized Structure-Adaptive Optimization. PhD thesis, 2019 [link]
  2. The Non-Uniform Fast Fourier Transform in Computed Tomography. MSc thesis, 2015 [link]

***********************************************************************************

Reviewer of:

ICML 2021, 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

Email: J.Tang@ed.ac.uk