🗓We've got our last #privacyinfra event for 2020 this Thursday at 10am PT, with privacy eng. talks from LinkedIn, Wikipedia, and more. #privacyeng Register here: zoom.us/webinar/regist…

Excited to present tomorrow at the virtual privacy engineering meetup–hosted by Transcend! LinkedIn Engineering

📺🎙 Today’s privacy_infra() #PrivacyEng event is about to begin (10am PT)! Join us at zoom.us/webinar/regist…

Nice connection between exponential noise and Permute-and-Flip!

The **Algorithms** group Microsoft Research Redmond is hiring! It is the sister group to our ML Foundations group, and has already strong presence in differential privacy and coding! Post Doc: careers.microsoft.com/us/en/job/9332… FTE: careers.microsoft.com/us/en/job/9332…

Did you miss TPDP 2020? If you were unable to attend, or want to watch again, videos of the talks are available here: tpdp.journalprivacyconfidentiality.org/2020/

CfP for the workshop on Theory and Practice of Differential Privacy (TPDP 2021, co-located with ICML Conference #ICML2021) is up! Deadline: May 28. Submit work on any aspects of DP! Co-chaired with Rachel Cummings. Invited speakers are Katrina Ligett and Ryan. tpdp.journalprivacyconfidentiality.org/2021/

Check out our fearless leader in Applied Research at LinkedIn Engineering talk about the great work from our team, including differential privacy!

An important result that has gone under-appreciated for a few years: the exponential mechanism is about twice as private as you think (at least under composition).

Originating from conversations at the 2020 Google Workshop on Federated Learning and Analytics (shorturl.at/myAY8), 26 Google AI researchers and 27 academic researchers began a year-long collaboration resulting in A Field Guide to Federated Optimization

Thanks for inviting me! Had a great time at #TPDP2021!

Another result of Durfee and Ryan that should be better known. They showed that the exponential mechanism in DP has better composition properties than generic DP algorithms. One application: Selecting the top k elements of some set. It turns out you can do it in one shot.