🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited about this new preprint with Daniil and @Kristo arxiv.org/abs/2402.16778 We show a Ω(log T) lower bound for Differentially Private Online learning, even for finite Littlestone classes. This shows a separation between DP and non-DP online learning in mistake bound model.

2 concurrent papers, one by Edith Cohen, Jelani Nelson, Lyu, Stemmer and Sarlós (x.com/jalajupadhyay/…) & the other by us solve our open problem presented in #COLT2022. (See Noah Golowich & Livni's upper bound) Interestingly, both have the same hard instance in the lower bound.

The call for this position is now public. This will be jointly supervised with Prof. Amir Yehudayoff at DIKU - Department of Computer Science, UCPH , Prof. Varun Kanade Oxford Comp Sci (including a stay in Oxford for 3-6 months), and myself. candidate.hr-manager.net/ApplicationIni… RTs appreciated

Very happy that this paper was accepted to #COLT2024 on the separation between private and non-private online learnability. Joint work with Daniil Dmitriev and Kristof Szabo. There are still few open problems that remain to fully settle this question :)

Open Postdoctoral position in Privacy (and unlearning) and Robustness in Machine Learning in University of Copenhagen to work with me! If you want to spend a couple of years working on these exciting topics in beautiful Copenhagen, Apply here employment.ku.dk/all-vacancies/…