Jingfeng Wu
@uuujf.bsky.social
Postdoc at Simons at UC Berkeley; alumnus of Johns Hopkins & Peking University; deep learning theory.
https://uuujf.github.io
https://uuujf.github.io
Pinned
Jingfeng Wu
@uuujf.bsky.social
· Sep 26
sharing a new paper w/ Peter Bartlett, @jasondeanlee.bsky.social @shamkakade.bsky.social, Bin Yu
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
sharing a new paper w/ Peter Bartlett, @jasondeanlee.bsky.social @shamkakade.bsky.social, Bin Yu
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
September 26, 2025 at 3:49 AM
sharing a new paper w/ Peter Bartlett, @jasondeanlee.bsky.social @shamkakade.bsky.social, Bin Yu
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
ppl talking about implicit regularization, but how good is it? We show it's surprisingly effective: GD dominates ridge for linear regression, w/ more cool stuff on GD vs SGD
arxiv.org/abs/2509.17251
Reposted by Jingfeng Wu
I wrote an op-ed on the world-class STEM research ecosystem in the United States, and how this ecosystem is now under attack on multiple fronts by the current administration: newsletter.ofthebrave.org/p/im-an-awar...
I’m an award-winning mathematician. Trump just cut my funding.
The “Mozart of Math” tried to stay out of politics. Then it came for his research.
newsletter.ofthebrave.org
August 18, 2025 at 3:45 PM
I wrote an op-ed on the world-class STEM research ecosystem in the United States, and how this ecosystem is now under attack on multiple fronts by the current administration: newsletter.ofthebrave.org/p/im-an-awar...
Reposted by Jingfeng Wu
Congratulations to our colleague and friend, former Simons Institute Associate Director Peter Bartlett, who will be delivering one of the plenary lectures for the 2026 International Congress of Mathematicians.
www.simonsfoundation.org/2025/07/11/m...
www.simonsfoundation.org/2025/07/11/m...
More Than 50 Simons Foundation Grantees to Speak at 2026 International Congress of Mathematicians
More Than 50 Simons Foundation Grantees to Speak at 2026 International Congress of Mathematicians on Simons Foundation
www.simonsfoundation.org
August 15, 2025 at 6:12 AM
Congratulations to our colleague and friend, former Simons Institute Associate Director Peter Bartlett, who will be delivering one of the plenary lectures for the 2026 International Congress of Mathematicians.
www.simonsfoundation.org/2025/07/11/m...
www.simonsfoundation.org/2025/07/11/m...
Reposted by Jingfeng Wu
My thoughts on the crucial importance of methodology on self-reported AI performance on mathematics competitions, and my policy on commenting on such reports going forward: mathstodon.xyz/@tao/1148814...
Terence Tao (@tao@mathstodon.xyz)
It is tempting to view the capability of current AI technology as a singular quantity: either a given task X is within the ability of current tools, or it is not. However, there is in fact a very wid...
mathstodon.xyz
July 19, 2025 at 10:37 PM
My thoughts on the crucial importance of methodology on self-reported AI performance on mathematics competitions, and my policy on commenting on such reports going forward: mathstodon.xyz/@tao/1148814...
Reposted by Jingfeng Wu
📣Join us at COLT 2025 in Lyon for a community event!
📅When: Mon, June 30 | 16:00 CET
What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community!
let-all.com/colt25.html
📅When: Mon, June 30 | 16:00 CET
What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community!
let-all.com/colt25.html
June 24, 2025 at 6:22 PM
📣Join us at COLT 2025 in Lyon for a community event!
📅When: Mon, June 30 | 16:00 CET
What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community!
let-all.com/colt25.html
📅When: Mon, June 30 | 16:00 CET
What: Fireside chat w/ Peter Bartlett & Vitaly Feldman on communicating a research agenda, followed by mentorship roundtable to practice elevator pitches & mingle w/ COLT community!
let-all.com/colt25.html
Sharing two new papers on accelerating GD via large stepsizes!
Classical GD analysis assumes small stepsizes for stability. However, in practice, GD is often used with large stepsizes, which lead to instability.
See my slides for more details on this topic: uuujf.github.io/postdoc/wu20...
Classical GD analysis assumes small stepsizes for stability. However, in practice, GD is often used with large stepsizes, which lead to instability.
See my slides for more details on this topic: uuujf.github.io/postdoc/wu20...
June 4, 2025 at 6:55 PM
Sharing two new papers on accelerating GD via large stepsizes!
Classical GD analysis assumes small stepsizes for stability. However, in practice, GD is often used with large stepsizes, which lead to instability.
See my slides for more details on this topic: uuujf.github.io/postdoc/wu20...
Classical GD analysis assumes small stepsizes for stability. However, in practice, GD is often used with large stepsizes, which lead to instability.
See my slides for more details on this topic: uuujf.github.io/postdoc/wu20...
Reposted by Jingfeng Wu
Jingfeng Wu, Pierre Marion, Peter Bartlett
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
https://arxiv.org/abs/2506.02336
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
https://arxiv.org/abs/2506.02336
June 4, 2025 at 5:26 AM
Jingfeng Wu, Pierre Marion, Peter Bartlett
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
https://arxiv.org/abs/2506.02336
Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression
https://arxiv.org/abs/2506.02336
Reposted by Jingfeng Wu
Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025!
📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models!
🗓️ Deadline: May 19, 2025
📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models!
🗓️ Deadline: May 19, 2025
May 9, 2025 at 5:10 PM
Announcing the first workshop on Foundations of Post-Training (FoPT) at COLT 2025!
📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models!
🗓️ Deadline: May 19, 2025
📝 Soliciting abstracts/posters exploring theoretical & practical aspects of post-training and RL with language models!
🗓️ Deadline: May 19, 2025
Reposted by Jingfeng Wu
We were very lucky to have Peter Bartlett visit @uwcheritoncs.bsky.social and give a Distinguished Lecture on "Gradient Optimization Methods: The Benefits of a Large Step-size." Very interesting and surprising results.
(Recording will be available eventually)
(Recording will be available eventually)
May 7, 2025 at 10:11 AM
We were very lucky to have Peter Bartlett visit @uwcheritoncs.bsky.social and give a Distinguished Lecture on "Gradient Optimization Methods: The Benefits of a Large Step-size." Very interesting and surprising results.
(Recording will be available eventually)
(Recording will be available eventually)
Reposted by Jingfeng Wu
I wrote a post on how to connect with people (i.e., make friends) at CS conferences. These events can be intimidating so here's some suggestions on how to navigate them
I'm late for #ICLR2025 #NAACL2025, but in time for #AISTATS2025 #ICML2025! 1/3
kamathematics.wordpress.com/2025/05/01/t...
I'm late for #ICLR2025 #NAACL2025, but in time for #AISTATS2025 #ICML2025! 1/3
kamathematics.wordpress.com/2025/05/01/t...
Tips on How to Connect at Academic Conferences
I was a kinda awkward teenager. If you are a CS researcher reading this post, then chances are, you were too. How to navigate social situations and make friends is not always intuitive, and has to …
kamathematics.wordpress.com
May 1, 2025 at 12:57 PM
I wrote a post on how to connect with people (i.e., make friends) at CS conferences. These events can be intimidating so here's some suggestions on how to navigate them
I'm late for #ICLR2025 #NAACL2025, but in time for #AISTATS2025 #ICML2025! 1/3
kamathematics.wordpress.com/2025/05/01/t...
I'm late for #ICLR2025 #NAACL2025, but in time for #AISTATS2025 #ICML2025! 1/3
kamathematics.wordpress.com/2025/05/01/t...
Reposted by Jingfeng Wu
Ruiqi Zhang, Jingfeng Wu, Licong Lin, Peter L. Bartlett
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
https://arxiv.org/abs/2504.04105
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
https://arxiv.org/abs/2504.04105
April 8, 2025 at 5:26 AM
Ruiqi Zhang, Jingfeng Wu, Licong Lin, Peter L. Bartlett
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
https://arxiv.org/abs/2504.04105
Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
https://arxiv.org/abs/2504.04105
Reposted by Jingfeng Wu
Join us for a week of talks on The Future of Language Models and Transformers at the Simons Institute. Talks by @profsanjeevarora.bsky.social, Azalia Mirhoseini, Kilian Weinberger and others. Mon, March 31 - Fri, April 4.
simons.berkeley.edu/workshops/future-language-models-transformers
simons.berkeley.edu/workshops/future-language-models-transformers
The Future of Language Models and Transformers
Transformers have now been scaled to vast amounts of static data. This approach has been so successful it has forced the research community to ask, "What's next?". This workshop will bring together re...
simons.berkeley.edu
March 31, 2025 at 4:22 PM
Join us for a week of talks on The Future of Language Models and Transformers at the Simons Institute. Talks by @profsanjeevarora.bsky.social, Azalia Mirhoseini, Kilian Weinberger and others. Mon, March 31 - Fri, April 4.
simons.berkeley.edu/workshops/future-language-models-transformers
simons.berkeley.edu/workshops/future-language-models-transformers