PeopleofSuperintelligence

Researcher

Jingwei Liang

Also known as 梁经纬

Jingwei Liang is a mathematician at Shanghai Jiao Tong University whose research covers non-smooth optimisation, data science and mathematical image processing. After studying for a mathematics PhD at Université de Caen Normandie from 2013 to 2017, he coauthored forward–backward splitting papers with Jalal Fadili and Gabriel Peyré for NIPS in 2014 and 2016. During his Cambridge postdoc he coauthored a 2018 ICML paper on SAGA and Prox-SVRG with Clarice Poon and Carola-Bibiane Schönlieb, and in 2020 he shared an ICML Outstanding Paper Award for a tuning-free plug-and-play algorithm for inverse imaging problems. He was a lecturer at Queen Mary University of London from November 2020 to June 2021, then moved to Shanghai Jiao Tong in 2021. A 2024 survey on stochastic optimisation for large-scale inverse problems, written with Matthias Ehrhardt, Zeljko Kereta and Junqi Tang, carries his name, and he is a tenure-track associate professor at the Institute of Natural Sciences and the School of Mathematical Sciences there.

Now at
Image and Optimization Group

Timeline

  1. 2013–2017

    PhD in mathematics at Caen

    He studies for a PhD in mathematics at GREYC, ENSICAEN and Université de Caen Normandie in France from 2013 to 2017.

  2. 2014–2016

    Forward–backward splitting at NIPS

    With Jalal Fadili and Gabriel Peyré, he presents a NIPS 2014 paper showing that the Forward–Backward algorithm identifies an active manifold in finitely many iterations and then converges linearly. In 2016, the same three authors present a multi-step inertial Forward–Backward method for non-convex problems at NIPS.

  3. 2017–2020

    Postdoc at Cambridge DAMTP

    He joins the Department of Applied Mathematics and Theoretical Physics at the University of Cambridge as a postdoctoral research associate in April 2017 and stays until August 2020.

  4. 2018

    SAGA and Prox-SVRG at ICML

    With Clarice Poon and Carola-Bibiane Schönlieb, he presents a local convergence analysis of the stochastic methods SAGA and Prox-SVRG at ICML 2018. The paper shows that both methods identify a smooth manifold in finitely many iterations and then enter a local linear convergence regime.

  5. 2020

    An ICML Outstanding Paper

    In 2020, he shares an ICML Outstanding Paper Award with Kaixuan Wei, Angelica Aviles-Rivero, Ying Fu, Carola-Bibiane Schönlieb and Hua Huang for Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems. A policy network, learned with deep reinforcement learning, sets the penalty parameter, the denoising strength and the terminal time automatically.

  6. November 2020–June 2021

    Lecturer at Queen Mary

    He works as Lecturer in Mathematical Data Science in the School of Mathematical Sciences at Queen Mary University of London from November 2020 to June 2021.

  7. 2024

    A guide to stochastic optimisation

    In 2024, he coauthors the survey A Guide to Stochastic Optimisation for Large-Scale Inverse Problems with Matthias J. Ehrhardt, Zeljko Kereta and Junqi Tang. The survey discusses variance reduction, acceleration and higher-order methods from the viewpoint of inverse problems.

  8. As of October 2026

    Associate professor at Shanghai Jiao Tong

    He is a tenure-track associate professor at the Institute of Natural Sciences and the School of Mathematical Sciences at Shanghai Jiao Tong University, a post he has held since July 2021. He is a member of the Image and Optimization Group.

Career

  1. Since 2021Shanghai Jiao Tong UniversityTenure-track associate professor
  2. NowImage and Optimization GroupMember
  3. 2020–2021Queen Mary University of LondonLecturer in Mathematical Data Science
  4. 2017–2020University of CambridgePostdoctoral research associate

Education

  1. 2017Université de Caen NormandiePhD
  2. 2017ENSICAENPhD
  3. 2017Université de Caen NormandiePhD

From the biography.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Jingwei Liang. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Shanghai Jiao Tong University. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  3. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Shanghai Jiao Tong University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Shanghai Jiao Tong University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Jingwei Liang yet. Send us a free-licensed photo.

  1. Jingwei Liang (梁经纬) ins.sjtu.edu.cn. Checked 21 October 2026.
  2. Local Linear Convergence of Forward--Backward under Partial Smoothness papers.nips.cc. Checked 21 October 2026.
  3. A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization proceedings.neurips.cc. Checked 21 October 2026.
  4. Local Convergence Properties of SAGA/Prox-SVRG and Acceleration proceedings.mlr.press. Checked 21 October 2026.
  5. ICML 2020 Awards icml.cc. Checked 21 October 2026.
  6. ICML 2020 Outstanding Paper Award | Cambridge Image Analysis damtp.cam.ac.uk. Checked 21 October 2026.
  7. Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems proceedings.mlr.press. Checked 21 October 2026.
  8. [2406.06342] A Guide to Stochastic Optimisation for Large-Scale Inverse Problems arxiv.org. Checked 21 October 2026.