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

[Berkeley Statistics @UCBStatistics]

UC Berkeley Statistics and the Department of Electrical Engineering and Computer Sciences (@Berkeley_EECS ) is hiring!

Details & apply: https://t.co/zBmPikvK6C

[Berkeley Statistics @UCBStatistics]

UC Berkeley Department of Statistics is hiring! We’re seeking applications for our Postdoctoral Neyman Fellow position.

Details & apply: https://t.co/5J19jUOrRZ

#Statistics #Probability #DataScience #FacultyJobs #UCBerkeley

[Dylan Foster 🐢 @canondetortugas]

A super exciting announcement: In January 2027, I'll be joining @UCBerkeley as an assistant professor in EECS and Statistics.

I'll be recruiting PhD students and postdocs this cycle, starting Fall 2027. If you're interested the science of RL and deep learning, please apply.

[Spencer Frei @sfrei_]

I'm hiring a Student Researcher to work on scaling laws at Google DeepMind! Project is for 19 weeks, starting winter/spring '27 (ideally: January '27), in-person in downtown SF. If you're interested, fill out this form: https://t.co/fh4Vzp0YnN

[Berkeley Statistics @UCBStatistics]

UC Berkeley Department of Statistics is hiring! We’re seeking applicants for a tenure-track Assistant Professor position in Statistics, Probability, and Data Science.

Details & apply: https://t.co/94KF5Sa0Ae

#BerkeleyStats #Probability #DataScience #FacultyJobs #UCBerkeley

[Juno KIM @junokim_ai]

What's the best way to solve linear regression? (No, it’s not least squares.)
In our new paper, we show that principal component regression (PCR) beats, up to constants, every monotone spectral filter (incl. gradient descent & ridge regression) on every problem instance! (1/8)

[Dimitris Papailiopoulos @DimitrisPapail]

Man it’s been like a month since navier stokes and nobody has used the AI Death Star to prove anything useful for Deep Learning. SAD!

[Simons Institute for the Theory of Computing @SimonsInstitute]

In September, we hosted a working group to think about how the TCS community should respond to AI progress. Their report, released yesterday, highlights 12 near-term actions that received broad support among the participants.

https://t.co/4Ddf8lC78s

[Ben Recht @beenwrekt]

Here’s my first attempt to grapple with AI companies’ conquest of mathematics and our new mathematical condition.

https://t.co/W7uMYInMIE

[Tony Feng @tonylfeng]

Second, I'm disturbed that an event which could have been celebrated as a triumph of human understanding, is instead headlined by ugly disputes.

The obsession with priority and prizes will become (much more) unhealthy in the presence of AI. My opinion is that all mathematical prizes should be abolished soon, with perhaps a gentle phaseout in the next year or two allowing only consideration of work that appeared pre June 2026. Traditional norms will have to be revisited, and egos put aside; I think the concept of individual priority and achievement will lose meaning in mathematics research, and the focus should be entirely on collective scientific understanding. This will be upsetting to many people, but I do not see how the community can proceed harmoniously otherwise.

In this spirit, I would like to give a generous account of events. Looking at the progress of Alpoge–Buckmaster, I am confident that they could eventually have gotten to Navier–Stokes on their own before long. This would also have been controversial, as accounts suggest that their progress (or at least, the proofs) came from internal Claude models, leveraged with industrial scale compute from Anthropic. Whatever the noble intentions at the origin of the project, it’s hard to imagine that alternate ending would not also have been paraded around as a corporate achievement.

I am also confident that OpenAI would have solved Navier–Stokes even if Buckmaster had never typed any information into ChatGPT. As I mentioned, other people were trying to push Sol and Astra along the same program. In the end, even the solutions to the Euler equation are appreciably different. But regardless, can OpenAI just come out and clearly answer the question: if users turn off “Improve the model for everyone”, do you in fact abstain from training on it altogether? If not, what exactly does that button do anyway?

[Peking University @PKU1898]

Huge congratulations to PKU alumni Wang Hong and Deng Yu, recipients of the 2026 Fields Medal — mathematics’ highest honor! 🧮

Announced at the 2026 International Congress of Mathematicians (ICM) in Philadelphia, the pair are among four mathematicians worldwide to claim this prestigious prize, awarded every four years to outstanding scholars under 40.

The awards are historic on several levels.

—First time two mathematicians who completed undergraduate studies in mainland China win the Fields Medal in the same year.

—Both joined Peking University as undergraduates in 2007.

—Wang Hong becomes only the third female Fields Medalist ever, the first Chinese woman, and the first recipient with a bachelor’s degree from a mainland Chinese university.

We are immensely proud of their extraordinary breakthroughs and lasting contributions to global mathematics.

[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.