Amir Balef
@amirbalef.bsky.social
PhD student in AutoML @ University of Tübingen
This insight led to MaxUCB, our new algorithm with strong theoretical guarantees and excellent empirical performance.
📍Meet @keggensperger.bsky.social at NeurIPS (San Diego) or @claireve.bsky.social and me at EurIPS (Copenhagen)!
💻 Code: github.com/amirbalef/CA...
(3/3)
📍Meet @keggensperger.bsky.social at NeurIPS (San Diego) or @claireve.bsky.social and me at EurIPS (Copenhagen)!
💻 Code: github.com/amirbalef/CA...
(3/3)
github.com
October 6, 2025 at 4:54 PM
This insight led to MaxUCB, our new algorithm with strong theoretical guarantees and excellent empirical performance.
📍Meet @keggensperger.bsky.social at NeurIPS (San Diego) or @claireve.bsky.social and me at EurIPS (Copenhagen)!
💻 Code: github.com/amirbalef/CA...
(3/3)
📍Meet @keggensperger.bsky.social at NeurIPS (San Diego) or @claireve.bsky.social and me at EurIPS (Copenhagen)!
💻 Code: github.com/amirbalef/CA...
(3/3)
“Max K-Armed Bandits should be perfect for HPO… but why are they never used?”
Because they are fundamentally harder than classic bandits and require proper assumptions. In the HPO setting, we identify exactly those assumptions and show how they enable efficient estimation of extremes.
(2/3)
Because they are fundamentally harder than classic bandits and require proper assumptions. In the HPO setting, we identify exactly those assumptions and show how they enable efficient estimation of extremes.
(2/3)
October 6, 2025 at 4:54 PM
“Max K-Armed Bandits should be perfect for HPO… but why are they never used?”
Because they are fundamentally harder than classic bandits and require proper assumptions. In the HPO setting, we identify exactly those assumptions and show how they enable efficient estimation of extremes.
(2/3)
Because they are fundamentally harder than classic bandits and require proper assumptions. In the HPO setting, we identify exactly those assumptions and show how they enable efficient estimation of extremes.
(2/3)