Jingfeng Wu

Assistant Professor @UCBStatistics @UCBerkeley
Deep Learning Theory, Statistical Learning, Optimization

[Jingfeng Wu @uuujingfeng]

sharing a new paper w Peter Bartlett, @jasondeanlee, @ShamKakade6, Bin Yu
ppl talking about implicit regularization, but how good is it? We show its surprisingly effective, that GD dominates ridge for all linear regression, w/ more cool stuff on GD vs SGD
https://t.co/oAVKiVgUUQ

[ICML Conference @icmlconf]

@ShamKakade6 gave an incredible talk this morning to a packed house! #icml2026

[Hongxun Wu @HongxunWu]

🧵(1/8) An @OpenAI internal reasoning LLM achieved an AI Math milestone: solving an open problem central to its mathematical subfield— in this case, the unit distance problem of discrete geometry.

We came across it in a side quest to truly push our model on the hardest problems.

[Thomas G. Dietterich @tdietterich]

Attention @arxiv authors: Our Code of Conduct states that by signing your name as an author of a paper, each author takes full responsibility for all its contents, irrespective of how the contents were generated. 1/

[Berkeley Statistics @UCBStatistics]

Professor of the Graduate School Peter Bartlett is one of six Berkeley faculty members recently inducted into the National Academy of Sciences in 2026!

#BerkeleyStats

[Simons Institute for the Theory of Computing @SimonsInstitute]

Thursday and Friday this week, a workshop on Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era, celebrating Peter Bartlett's 60th birthday.

https://t.co/nc06LGLeH3

[Jingfeng Wu @uuujingfeng]

@Jere_je_je @JohnsHopkins @JHUBME Congrats!

[Mahdi Soltanolkotabi @mahdisoltanol]

Fun new theory paper on data reuse:

𝗙𝗨𝗟𝗟-𝗕𝗔𝗧𝗖𝗛 𝗚𝗗 can beat 𝗢𝗡𝗘-𝗣𝗔𝗦𝗦 𝗦𝗚𝗗 by a log-factor in samples.

Same single-index model, same data:

→ 𝗚𝗗 recovers with n ≈ d
→ 𝗦𝗚𝗗 needs n ≳ d log d

https://t.co/ZA0LQCpOU1

[Weijie Su @weijie444]

It is my tremendous honor and privilege to receive the 2026 COPSS Presidents' Award. Statistics is powerful and will only grow more vital in the AI age. Grateful to my mentors, collaborators, colleagues, and students who made this journey possible.

[The Wharton School @Wharton]

Congratulations to Prof. Weijie Su (@weijie444) from our Statistics and Data Science Department on being named the recipient of this year's Committee of Presidents of Statistical Societies (@COPSSNews) Presidents' Award: https://t.co/xBXjzUndEo

The honor is given annually to a young member of the statistical community in recognition of outstanding contributions to the profession of statistics.

It's jointly sponsored by five statistical societies: @AmstatNews,
@ENAR_ibs, @InstMathStat, @SSC_stat, and @WNAR_ibs.

[Data Science Institute @DSI_UChicago]

Don't miss the next Statistics and DSI Joint Colloquium!

@uuujingfeng, postdoc fellow at @SimonsInstitute at @UCBerkeley, presents 'Towards a Less Conservative Theory of Machine Learning: Unstable Optimization and Implicit Regularization' on Thursday, February 5th at DSI

[Arya Mazumdar @MountainOfMoon]

Just went through the slides on stability in optimization and generalization, from the @NeurIPSConf tutorial this year by @uuujingfeng @yuxiangw_cs and Maryam Fazel. This is so good - highly recommend this. https://t.co/roqqatKCrC

[TTIC @TTIC_Connect]

Thursday, December 11th at 11AM: Talks at TTIC presents Jingfeng Wu (@uuujingfeng) of @SimonsInstitute with a talk titled "A Statistical View on Implicit Regularization: Gradient Descent Dominates Ridge." Please join us in Room 530, 5th floor.

[Spencer Frei @sfrei_]

I'm hiring a Student Researcher to work on scaling laws at Google DeepMind! Project is for 16 weeks, starting spring/summer '26, in-person in SF (pic from the amazing office). If you're interested, fill out this form: https://t.co/nnRmY2hqeL

[Jingfeng Wu @uuujingfeng]

Together with @yuxiangw_cs and Maryam Fazel, we are excited to present our tutorial "Theoretical Insights on Training Instability in Deep Learning" tomorrow at #NeurIPS2025!
Link: https://t.co/e4T1eI45Ql
*picture generated by Gemini

[Berkeley Statistics @UCBStatistics]

UC Berkeley Department of Statistics is hiring! We’re seeking applicants for up to three approved tenure-track positions at the Assistant Professor level in Statistics, Probability and AI.

Details & apply: https://t.co/tcail7NkAR

#AI #Statistics #Probability #UCBerkeley

[Sham Kakade @ShamKakade6]

1/6 Introducing Seesaw: a principled batch size scheduling algo. Seesaw achieves theoretically optimal serial run time given a fixed compute budget and also matches the performance of cosine annealing at fixed batch size.

[Jeremy Cohen @deepcohen]

Even with full-batch gradients, DL optimizers defy classical optimization theory, as they operate at the *edge of stability.*

With @alex_damian_, we introduce "central flows": a theoretical tool to analyze these dynamics that makes accurate quantitative predictions on real NNs.

[Jason Lee @jasondeanlee]

Gd dominates ridge regression but not sgd! Surprising that such simple things aren't known for linear regression

[Jingfeng Wu @uuujingfeng]

my slides: https://t.co/TjL0HZak7u

[Jingfeng Wu @uuujingfeng]

sharing a new paper w Peter Bartlett, @jasondeanlee, @ShamKakade6, Bin Yu
ppl talking about implicit regularization, but how good is it? We show its surprisingly effective, that GD dominates ridge for all linear regression, w/ more cool stuff on GD vs SGD
https://t.co/oAVKiVgUUQ