Argyris Mouzakis
@argymouzCS PhD Student @ UWaterloo with focus on Statistics, Machine Learning and Differential Privacy
Similar User
@zakynthinou
@thejonullman
@sarakodeiri
@kfountou
@LesterMackey
@SurbhiGoel_
@WeinNicole
@AmritaRoyChowd8
@GolowichNoah
@praveshkkothari
@AdenIshaq
@SatchitSivakum1
@sitanch
@roliveira641
@HaghifamMahdi
After a long but very thoughtful review and revision process, this paper was finally accepted to the Journal of the American Statistical Association (JASA)! Congrats to the junior authors Matthew Regehr (@matt19234), Argyris Mouzakis (@argymouz), and Vikrant Singhal (@vkerdos).
🧵 "A Bias-Variance-Privacy Trilemma for Statistical Estimation," with @argymouz, Matthew Regehr, @vkerdos, @shortstein, and @thejonullman arxiv.org/abs/2301.13334 Private estimators MUST be biased! 1/n
The simplest possible optimal PAC learner? New arXiv preprint: arxiv.org/abs/2403.08831
🧵New paper: "Not All Learnable Distribution Classes are Privately Learnable" to appear in #ALT2024. We refute a conjecture of @ashtiani_hassan We show that there exists a learnable distribution class which is not privately learnable. w @markmbun @argymouz @vkerdos 1/n
🧵Highlighting a SODA 2024 accepted paper, "Sorting and Selection in Rounds with Adversarial Comparisons," authored *solely* by @WaterlooMath undergraduate Chris Trevisan. This is the only single-authored paper by an undergrad in this SODA, a huge achievement!! Read on 👇1/n
Thanks @thegautamkamath both for posting this and for advising and supporting me! It's a privilege to be part of @TheSalonML ! Also, thanks to all of my co-authors and mentors for their support (Matt Regehr, @vkerdos, @shortstein and @thejonullman)!
Congratulations to my PhD student Argyris Mouzakis (@argymouz) on being awarded the Onassis Foundation Scholarship! This scholarship has supported some of the most brilliant scientists in the Greek diaspora, and Argyris is no exception. argymouz.github.io
Congrats to Duchi-Haque-Kuditipudi (arxiv.org/abs/2301.07078) and Brown-Hopkins-Smith (arxiv.org/abs/2301.12250) on #COLT2023 best student paper for their works on differentially private mean estimation! Wanna know what their works are about? Read on 🧵1/n
#COLT2023 Mark Fulk award for best student paper is shared by two papers
I was at a sensational combinatorics seminar in Cambridge yesterday, reminiscent of the time I had been tipped off that Andrew Wiles's seminar at the Newton Institute on Wednesday 23rd June 1993 might be worth going to. 🧵 arxiv.org/abs/2303.09521
Congrats to @UWCheritonCS colleagues Niki Hasrati (@niki_hasrati) & Shai Ben-David (@shaibendavid5) on best paper at #ALT2023. Main result shows when an online learner must be computable, it's no longer characterized by Littlestone dimension. Check it out: arxiv.org/abs/2302.04357
Congratulations to Niki Hasrati @niki_hasrati and Shai Ben-David for their paper "On Computable Online Learning" that has been selected for the best paper award at #ALT2023. We thank the authors for their contribution and look forward to celebrating soon in Singapore (Feb 20-23)!
⚠️🚨BONUS TWEET 🚨⚠️ Be sure to also check out this other paper posted at the same time, by @thesasho and Haohua Tang, also focused on unbiased algorithms in differential privacy. Despite similarities in the titles, the settings are mostly different. arxiv.org/abs/2301.13850 9/8
Special congratulations to Matt (currently a Master's student - he's not on twitter afaik) who, out of the junior people, is the person who lead this project!
🧵 "A Bias-Variance-Privacy Trilemma for Statistical Estimation," with @argymouz, Matthew Regehr, @vkerdos, @shortstein, and @thejonullman arxiv.org/abs/2301.13334 Private estimators MUST be biased! 1/n
#NeurIPS2022 Accepted Papers: nips.cc/Conferences/20… @NeurIPSConf
3 papers on efficient and differentially private learning of Gaussians in #colt2022 ! Interestingly each paper uses a different approach. Core challenge is handling covariances with high condition numbers. You cannot simply add isotropic noise; it has to "scale" with data [1/5]
ICML 2022 Accepted Papers: icml.cc/Conferences/20… #ICML2022 @icmlconf
A really nice paper on lower bounds for private estimation by @thegautamkamath, Argyris Mouzakis, and @vkerdos 1/4 arxiv.org/abs/2205.08532
United States Trends
- 1. #SNME 144 B posts
- 2. Jeanty 55 B posts
- 3. Heisman 123 B posts
- 4. Travis Hunter 96,3 B posts
- 5. #UFCTampa 20,8 B posts
- 6. #SaturdayNightsMainEvent 6.001 posts
- 7. Chelsea 139 B posts
- 8. Michael Johnson 3.223 posts
- 9. Deion 9.403 posts
- 10. Jesse Ventura 5.352 posts
- 11. Airdrop 2 1,7 Mn posts
- 12. #HE12MAN 14,4 B posts
- 13. Winged Eagle 9.489 posts
- 14. Gunther 12,2 B posts
- 15. UConn 6.087 posts
- 16. Rhea 18,1 B posts
- 17. Sengun 3.706 posts
- 18. #AEWCollision 10,2 B posts
- 19. Lil Wayne 6.443 posts
- 20. Kevin Owens 13,3 B posts
Who to follow
-
Lydia Zakynthinou
@zakynthinou -
Jonathan Ullman
@thejonullman -
Sara Kodeiri
@sarakodeiri -
Kimon Fountoulakis
@kfountou -
Lester Mackey
@LesterMackey -
Surbhi Goel
@SurbhiGoel_ -
Nicole Wein
@WeinNicole -
Amrita Roy Chowdhury
@AmritaRoyChowd8 -
Noah Golowich
@GolowichNoah -
Pravesh K. Kothari
@praveshkkothari -
Ishaq Aden-Ali
@AdenIshaq -
Satchit Sivakumar
@SatchitSivakum1 -
Sitan Chen
@sitanch -
Rafael Oliveira
@roliveira641 -
Mahdi Haghifam
@HaghifamMahdi
Something went wrong.
Something went wrong.