Idan Mehalel

I am a direct-track, final year PhD student at the Computer Science department, Technion, where I am fortunate to be advised by Yuval Filmus and Shay Moran. I am working primarily on Foundations of Machine Learning. You can check out my c.v. here.

Contact information

Email: idanmehalel@gmail.com

Office: 513, Taub building, Computer Science department, Technion.

Updates

Preprints

Yuval Filmus, Steve Hanneke, Idan Mehalel and Shay Moran. Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs. Submitted.

Publications

Click the bullet for additional relevant links.

Idan Mehalel, Ananth Raman, Vinod Raman, Unique Subedi and Ambuj Tewari. Multiclass Online Learnability Under Bandit Feedback. ALT 2024.

Yuval Filmus and Idan Mehalel. Optimal sets of questions for Twenty Questions. SIAM Journal on Discrete Mathematics (SIDMA), 2024.
Yuval Filmus, Steve Hanneke, Idan Mehalel and Shay Moran. Optimal Prediction using Expeft Advice and Randomized Littlestone
DImensionCOLT 2023.
Resolves several long standing open questions from the 90’s.
Steve Hanneke, Amin Karbasi, Mohammad Mahmoody, Idan Mehalel and Shay Moran. On Optimal Learning Under Targeted Data Poisoning. NeurIPS 2022.
Spotlight Presentation
Yuval FIlmus, Idan Mehalel and Shay Moran. A Resiliant Distributed Boosting Algorithm. ICML 2022.

Awards

  • Technion Computer Science department research excellence scholarship, Spring 2023.

Teaching

  • Logic for Computer Science (2022-2023)
  • Topics in Machine Learning Theory (2021)
  • Combinatorics for Computer Science (2019-2022)

The Technion’s “theory lunch

I am the organizer of the Technion’s weekly theory of computing seminar (a.k.a “theory lunch”). Besides for an interesting talk, the seminar offers an additional self explanatory activity :-).

Please e-mail me if you want to give a talk!

Design a site like this with WordPress.com
Get started