Jennifer Sun

PhD candidate @Princeton ORFE

[Jennifer Sun @jsun105]

@denizzokt @HazanPrinceton thank you!!!

[Elad Hazan @HazanPrinceton]

My student @jsun105 successfully defended her (excellent) thesis “Limited Feedback Models in Online Control" yesterday, it is available at:
https://t.co/M411tTSfhU
Congrats Dr. Sun!!

[Elad Hazan @HazanPrinceton]

My talk on spectral transformers, given at Princeton workshop on learning in dynamical systems, is now online:
https://t.co/nBkxfOLnvV

[Elad Hazan @HazanPrinceton]

Fantastic defense today by my student Nataly Brukhim, who deeply thought about new directions in boosting for the last 6 years, excellent talk & thesis, highly recommend the papers!: https://t.co/meF8iPuScc
(Rob Schapire, one of the founders of boosting, joined the committee)

[Elad Hazan @HazanPrinceton]

🧵1/3: population dynamics are important for the study of epidemiology, i.e. spread of infectious diseases, and controlling hospital flows. Recent work with @Golowich, Zhou Lu, Dhruv Rohatgi and @jsun105, on online control in population dynamics:
https://t.co/i7mAbKZPyy

[Learning Theory Alliance @let4all]

A new technical blog post by Nataly Brukhim and Chirag Pabbaraju (@cherry_pub), covering some of their breakthrough works on characterizing multiclass PAC learning. Check it out!
https://t.co/MnnxYWMO8K

[Elad Hazan @HazanPrinceton]

All in due time... 20 years after "Online Newton Step", comes "Bandit Newton Step" :-)
work with my fantastic student @jsun105 and my colleagues in Google India, Arun Suggala and Praneeth Netrapalli
https://t.co/kNwQ5pKkum

[Elad Hazan @HazanPrinceton]

most exciting paper *ever* from our @GoogleAI lab at @Princeton: @naman33k @danielsuo @XinyiChen2
https://t.co/aSkBZJ6S9t
*** Convolutional filters predetermined by the theory, no learning needed! ***

[Elad Hazan @HazanPrinceton]

@jsun105 the poster team, w/o Varun who couldn't make it

[Elad Hazan @HazanPrinceton]

Group dinner at NOLA, joined by some of our amazing alumni:

[Elad Hazan @HazanPrinceton]

Fun collaboration w. @FeinbergVlad , @XinyiChen2 @jsun105 and @_arohan_ on the use of frequent directions sketching for optimization, check it out in NeurIPS and Vlad's blog post!!

[Elad Hazan @HazanPrinceton]

I'll be teaching AI alignment & safety this fall https://t.co/gB55brOWf9
despite being a "graduate seminar", Princeton undergrads: you are very welcome!!
Glad to see other new academic courses, i.e. at Toronto U by @RogerGrosse

[Elad Hazan @HazanPrinceton]

Rate optimal bandit LQG/LQR with semi-adversarial noise, w. students Jennifer Sun @jsun105 and Stephen Newman:
https://t.co/6D9A8JiIem