Jingfeng Wu  |  吴京风

I am a postdoc fellow at the Simons Institute at UC Berkeley hosted by Peter Bartlett and Bin Yu. I am a part of the NSF/Simons Collaboration on the Theoretical Foundations of Deep Learning. I received my Ph.D. in Computer Science at Johns Hopkins University, advised by Vladimir Braverman.

I work on the theory and algorithms for machine learning. I am interested in deep learning theory, optimization, and statistical learning.

Email  |  arXiv  |  Google Scholar

JW
Short bio

Jingfeng Wu is a postdoctoral fellow at the Simons Institute for the Theory of Computing at UC Berkeley. His research focuses on deep learning theory, optimization, and statistical learning. He earned his Ph.D. in Computer Science from Johns Hopkins University in 2023. Prior to that, he received a B.S. in Mathematics (2016) and an M.S. in Applied Mathematics (2019), both from Peking University. In 2023, he was recognized as a Rising Star in Data Science by the University of Chicago and UC San Diego.

Tutorial@NeurIPS'25: Theoretical Insights on Training Instability in Deep Learning

News

  • [12/2025] Invited talk at TTIC.
  • [12/2025] Presenting a tutorial at NeurIPS 2025 with Yu-Xiang and Maryam.
  • [09/2025] Invited talks at Yale, UPenn, JHU, MIT, Harvard, NYU, Columbia.
  • [09/2025] Two papers accepted to NeurIPS 2025.
  • [07/2025] Invited talk at the 6th Youth in High-Dimensions Conference.
  • [05/2025] Invited talk at SIAM DS25.
  • [05/2025] Three papers accepted to ICML 2025.
  • [02/2025] Organizing a deep learning theory workshop at Simons.
  • [01/2025] One paper accepted to ICLR 2025.
Prior to 2025
  • [09/2024] Three papers accepted to NeurIPS 2024; huge congrats to Yuhang, Licong, and Ruiqi!!
  • [05/2024] One paper accepted to COLT 2024.
  • [03/2024] Invited talk at UCLA CS.
  • [02/2024] Invited talk at UC Berkeley Biostatistics.
  • [01/2024] Two papers accepted to ICLR 2024.
  • [10/2023] Selected as Rising Star in Data Science by UChicago and UCSD.
  • [09/2023] Two papers accepted to NeurIPS 2023.
  • [08/2023] Joining the Simons Institute at UC Berkeley as a postdoc.
  • [06/2023] Defended my PhD dissertation!
  • [05/2023] One paper accepted to CoLLAs 2023; congrats to Haoran!
  • [04/2023] One paper accepted to ICML 2023.
  • [09/2022] Two papers accepted to NeurIPS 2022.
  • [06/2022] Interning at Google Research Seattle.
  • [05/2022] One paper accepted to ICML 2022 as long presentation!
  • [01/2022] One paper accepted to AISTATS 2022.
  • [12/2021] Passed the PhD candidacy exam.
  • [09/2021] Two papers accepted to NeurIPS 2021.
  • [05/2021] Awarded MINDS Summer Data Science Fellowship!
  • [05/2021] One paper accepted to COLT 2021.
  • [02/2021] In a relationship with Yuan, happy Valentine's day~
  • [01/2021] One paper is accepted to ICLR 2021.
  • [05/2020] Two papers accepted to ICML 2020.
  • [09/2019] Joining Hopkins. Veritas vos liberabit!
  • [06/2019] Graduated from Peking University.
  • [04/2019] One paper accepted to ICML 2019.
  • [03/2019] One paper accepted to CVPR 2019 as an oral presentation.
  • [12/2018] Looking for a Ph.D. position in machine learning.

Selected Papers (All Papers)

* indicates equal contribution or alphabetical order

Optimization with Large Stepsizes (Slides)

Statistical Views on Implicit Regularization (Slides, Slides')

Implications of Implicit Regularization

Margin Theory for Neural Networks

Invited Talks

  • A Statistical View on Implicit Regularization: GD Dominates Ridge
    • [12/2025] TTIC, Talk at TTIC, hosted by Nati Srebro
    • [10/2025] Columbia, Machine Learning and AI Seminar, hosted by Daniel Hsu
    • [10/2025] NYU, Math and Data Seminar, hosted by Matus Telgarsky
    • [09/2025] Yale, Statistics & Data Science Seminar, hosted by Theodor Misiakiewicz, Omar Montasser
  • Reimagining Gradient Descent: Large Stepsize, Oscillation, and Acceleration
    • [10/2025] Harvard, Talk at Kempner, hosted by Sham Kakade
    • [09/2025] MIT, Talk at LIDS, hosted by Pablo Parrilo
    • [09/2025] JHU, CS Theory Seminar, hosted by Vova Braverman
    • [09/2025] UPenn, Group Seminar, hosted by Jason Altschuler
    • [06/2025] MPI & UCLA, Math Machine Learning Seminar, hosted by Guido Montufar
    • [05/2025] SIAM DS25, Dynamical Systems for Machine Learning, hosted by Molei Tao
    • [01/2025] UCLA, Level Set Meeting, hosted by Shu Liu, Stanley Osher
  • A Statistical View on Implicit Regularization: GD for Logistic Regression
    • [07/2025] ICTP, 6th Youth in High-Dimensions Conference, hosted by Marco Mondelli et al.
    • [02/2025] UC Berkeley, Deep Learning Theory Workshop, hosted by Peter Bartlett et al.
Prior to 2025

Services

People

Family

Recent Student Collaborators

Yuhang Cai    Licong Lin    Ruiqi Zhang   

Collaborators

Peter Bartlett    Vladimir Braverman    Zixiang Chen    Dean Foster    Udaya Ghai    Quanquan Gu    Peter Kairouz    Sham Kakade    Jason Lee    Haoran Li    Xuheng Li    Michael Lindsey    Pierre Marion    Song Mei    Depen Morwani    Matus Telgarsky    Nikhil Vyas    Lin Yang    Bin Yu    Hanlin Zhang    Wennan Zhu    Dongruo Zhou    Kangjie Zhou    Difan Zou