Hossein Mobahi's Avatar

Hossein Mobahi

@thegradient.bsky.social

Senior Research Scientist at Google DeepMind. I ∈ Optimization ∩ Machine Learning. Fan of IronMaiden🀘.Here to discuss research πŸ€“

2,091 Followers  |  365 Following  |  10 Posts  |  Joined: 16.11.2024  |  1.5366

Latest posts by thegradient.bsky.social on Bluesky

Thanks Kevin! This is so great and must be very calming to watch.

21.04.2025 20:16 β€” πŸ‘ 0    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Google PhD fellowship program The Google PhD Fellowship Program recognizes outstanding graduate students doing exceptional work in computer science, related disciplines, or promising research areas.

Applications for the global Google PhD Fellowship Program opens on Apr 10th. Fellowships directly support graduate students doing exceptional and innovative research in computer science and related fields as they pursue their PhD. Learn more and apply by May 15 at goo.gle/phdfellowship.

12.03.2025 00:05 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
Preview
Avoiding spurious sharpness minimization broadens applicability of SAM Curvature regularization techniques like Sharpness Aware Minimization (SAM) have shown great promise in improving generalization on vision tasks. However, we find that SAM performs poorly in domains l...

(2/2) Not at UCLA but interested in this topic? Check arxiv.org/abs/2502.02407. Thanks to our fantastic intern Sidak (soon to return full-time!) for leading this project, along with collaborators Yann and Atish. Thanks to my UCLA host @baharanm.bsky.social for the seminar invitation!

07.02.2025 18:58 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0
CS 201 | Hossein Mobahi, Google DeepMind | CS

(1/2) Ever wondered why Sharpness-Aware Minimization (SAM) yields greater generalization gains in vision than in NLP? I'll discuss this at UCLA's CS-201 seminar on February 18th, relating it to the balance of SAM's impact on logit statistics vs model geometry.
cs.ucla.edu/upcoming-eve...

07.02.2025 18:56 β€” πŸ‘ 8    πŸ” 1    πŸ’¬ 1    πŸ“Œ 0

Congratulations Ev!

23.01.2025 18:27 β€” πŸ‘ 3    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

Oops! Foreseeing a sudden surge in Bluesky’s server traffic until you are all caught up πŸ˜ƒ

05.01.2025 23:17 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

Hi folks! I'm excited to be on BlueSky! I'm looking forward to posting about computer science research, ML, scientific advances, tasty food, nature, and making groan-worthy puns.

05.01.2025 21:48 β€” πŸ‘ 479    πŸ” 42    πŸ’¬ 45    πŸ“Œ 5

2/2

Algorithms & optimization
Fundamentals & Applied Science
Health research
HCI
Machine learning & data mining
Machine perception
Natural language processing
Networking
Privacy, Safety, and Security
Quantum computing
Software engineering & programming languages
Systems

20.12.2024 19:05 β€” πŸ‘ 2    πŸ” 0    πŸ’¬ 0    πŸ“Œ 0

1/2 Just a reminder about Google Research Scholar Program, providing up to $60K unrestricted gifts to recognize early-career professors and support world-class research at institutions around the world. This year, we are particularly interested in the following research areas...

20.12.2024 19:04 β€” πŸ‘ 12    πŸ” 5    πŸ’¬ 1    πŸ“Œ 0
Preview
Research scholar program Overview

Applications are open for the Google's Research Scholar Program, a program that supports early-career professors conducting research in fields relevant to Google. Learn more and apply by January 27 at goo.gle/RS

13.12.2024 21:29 β€” πŸ‘ 4    πŸ” 0    πŸ’¬ 0    πŸ“Œ 1

We'll soon review internship applicants for our reasoning group; please submit and ping me if you haven't already!! Can't wait to work with you!!

05.12.2024 18:11 β€” πŸ‘ 5    πŸ” 2    πŸ’¬ 0    πŸ“Œ 0

Just created the Starter Pack for Optimization Researchers to help you on your journey into optimization! πŸš€

Did I miss anyone? Tag them or let me know what to add!

go.bsky.app/VjpyyRw

23.11.2024 23:59 β€” πŸ‘ 38    πŸ” 8    πŸ’¬ 14    πŸ“Œ 0

New starter pack! go.bsky.app/GZ4hZzu

28.10.2024 09:43 β€” πŸ‘ 42    πŸ” 19    πŸ’¬ 7    πŸ“Œ 5

For those who don’t feel like they fit into my Grumpy Machine Learners list (which I still need to update based on 100+ requests) I’ve created another starter pack:

go.bsky.app/Js7ka12

(Self) nominations welcome.

22.11.2024 18:40 β€” πŸ‘ 79    πŸ” 13    πŸ’¬ 37    πŸ“Œ 1

Just put together a starter pack for Deep Learning Theory. Let me know if you'd like to be included or suggest someone to add to the list!

go.bsky.app/2qnppia

22.11.2024 21:35 β€” πŸ‘ 88    πŸ” 32    πŸ’¬ 29    πŸ“Œ 5

Dude! These packs are getting out of control πŸ€ͺ

20.11.2024 00:19 β€” πŸ‘ 1    πŸ” 0    πŸ’¬ 1    πŸ“Œ 0

@thegradient is following 19 prominent accounts