Christian Lebeda
@christianlebeda.bsky.social
Reposted by Christian Lebeda
150 years ago the first women were enrolled at University of Copenhagen. To celebrate, four of my awesome BARC colleagues are arranging the WAVE workshop on October 10th.
Amazing speakers and panelists, full-day catering, and Copenhagen culture night in the evening! Join us!
t.co/zIeUnYVXMC
Amazing speakers and panelists, full-day catering, and Copenhagen culture night in the evening! Join us!
t.co/zIeUnYVXMC
https://barc.ku.dk/wave-conference/
t.co
September 22, 2025 at 6:44 PM
150 years ago the first women were enrolled at University of Copenhagen. To celebrate, four of my awesome BARC colleagues are arranging the WAVE workshop on October 10th.
Amazing speakers and panelists, full-day catering, and Copenhagen culture night in the evening! Join us!
t.co/zIeUnYVXMC
Amazing speakers and panelists, full-day catering, and Copenhagen culture night in the evening! Join us!
t.co/zIeUnYVXMC
Reposted by Christian Lebeda
New differential #privacy textbook in town: "DP in Artificial Intelligence: From Theory to Practice", by @nandofioretto.bsky.social and @vanhentenryck.bsky.social. Open access, w/ chapters by @jubaz.bsky.social, @grahamrc.bsky.social, and @stein.ke!
www.nowpublishers.com/article/Book...
www.nowpublishers.com/article/Book...
August 25, 2025 at 10:45 PM
New differential #privacy textbook in town: "DP in Artificial Intelligence: From Theory to Practice", by @nandofioretto.bsky.social and @vanhentenryck.bsky.social. Open access, w/ chapters by @jubaz.bsky.social, @grahamrc.bsky.social, and @stein.ke!
www.nowpublishers.com/article/Book...
www.nowpublishers.com/article/Book...
Reposted by Christian Lebeda
I wrote a post explaining why, in practice, privacy amplification by subsampling doesn't quite work as well as promised. This is a significant problem for differentially private machine learning applications, but I don't know if this is as widely known as it should be.
Limits of Privacy Amplification by Subsampling
Limits of Privacy Amplification by Subsampling
In our previous post we gave a brief introduction to privacy amplification by subsampling.
The high-level story is that we can make differentially private algorithms faster by runninng them on a subsa...
differentialprivacy.org
April 21, 2025 at 7:22 PM
I wrote a post explaining why, in practice, privacy amplification by subsampling doesn't quite work as well as promised. This is a significant problem for differentially private machine learning applications, but I don't know if this is as widely known as it should be.
Reposted by Christian Lebeda
Opportunity to do a PhD in a wonderful city, at a great university, with a fantastic supervisor! x.com/ioanabercea/...
Ioana O. Bercea on X: "I’m recruiting! Please help spread the word! 2PhDs available at KTH Royal Institute of Technology, in the area of Theoretical Computer Science. Deadline is April 3rd, 2025. More details here: https://t.co/rbDT01n5XI" / X
I’m recruiting! Please help spread the word! 2PhDs available at KTH Royal Institute of Technology, in the area of Theoretical Computer Science. Deadline is April 3rd, 2025. More details here: https://t.co/rbDT01n5XI
x.com
March 20, 2025 at 8:53 AM
Opportunity to do a PhD in a wonderful city, at a great university, with a fantastic supervisor! x.com/ioanabercea/...
Reposted by Christian Lebeda
Looking for a PhD position or a post-doc position in theoretical computer science? Consider applying to one of our calls, closing January 10! barc.ku.dk/career/
Career Opportunities – University of Copenhagen
barc.ku.dk
January 6, 2025 at 7:21 AM
Looking for a PhD position or a post-doc position in theoretical computer science? Consider applying to one of our calls, closing January 10! barc.ku.dk/career/