I agree that Dwork-Roth is written for a rather mathematical audience. The book you linked is really great for engineers who want to apply DP. But I think if you want to do *research* in DP, the ideal reference exists in a space between these two.
@thegautamkamath
-
TPDP Workshop: Annual Free DP Community Event and Networking
By
–
For the DP community, we have a fun workshop every year, TPDP. This is a free-to-attend, high-acceptance rate venue where a large number of DP researchers go. Great opportunity to meet folks and learn about the latest work. Favorite event of the year. https://
tpdp.journalprivacyconfidentiality.org 8/n -
Making Advanced Learning Theory Research More Accessible Through Blog Posts
By
–
Beyond the basics: w/ a huge & dense literature, papers building on top of each other, it's hard to jump into research. Accessible technical material of more advanced topics is helpful. With @let4all we solicit and curate learning theory blog posts: https://
let-all.com/blog/ 4/n -
Differential Privacy: Dwork, Rothblum’s Monograph and Educational Resources
By
–
In the DP realm, Dwork and @Aaroth wrote a great monograph a decade ago (
https://
cis.upenn.edu/~aaroth/Papers
/privacybook.pdf
…). I (and others) have uploaded courses on the topic, videos and all (
https://
x.com/thegautamkamat
h/status/1306975126790037512
…). 3/n -
Importance of Open Educational Materials for Machine Learning Newcomers
By
–
One very important technical tool is good open introductory educational material: textbooks, lecture notes, videos. O/W it's very difficult for newcomers w/o connections to learn the basics. See eg the classic @shai_s_shwartz @shaibendavid5 book https://
cs.huji.ac.il/~shais/Underst
andingMachineLearning/
… 2/n -
Evolution of Top AI Publication Venues Between 2013 and 2024
By
–
Sources: https://web.archive.org/web/20130409084519/https://scholar.google.com.au/citations?view_op=top_venues&hl=en&vq=eng_artificialintelligence
… https://web.archive.org/web/20240826235558/https://scholar.google.com.au/citations?view_op=top_venues&hl=en&vq=eng_artificialintelligence
… -
H-index explosion in top AI conferences 2013 to 2024
By
–
H-index of top 20 publication venues in AI, April 2013 versus today. 2013: NeurIPS (37), ICML (65), ICLR (did not exist)
2024: NeurIPS (337), ICML (268), ICLR (304) Please stop writing so many papers… -
CUDA Installation Challenge and Potential Interview Questions
By
–
"Install CUDA without bricking your personal laptop. You have 6 hours." Jokes aside, sounds like a great initiative. What type of questions could they ask?
-
TMLR partnership expansion with ICLR for 2025
By
–
2024: TMLR Featured Certifications (~spotlight+ quality) were welcome to present at ICLR 2025: broader set of TMLR papers will be welcome, based on AE recommendation and other signals TY ICLR for the partnership!
-
Combating Reviewer Apathy Through Personal Connection and Communication
By
–
We complain a lot about reviewer apathy. I think connecting people with the various roles is really important in fighting that. Eg, for NeurIPS ACing, I a) make sure my reviewers know who I am (o/w anon by default), & b) email reminders from my personal acc (not generic OR ones)