Amirreza Shaeiri
4 papers · 2025–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
Top co-authors
Research topics
Keywords
littlestone tree
(2)
agnostic setting
(2)
bandit feedback
(2)
massart noise
(1)
expected regret
(1)
realizable setting
(1)
universal learnability
(1)
multiclass online learning
(1)
agnostic to realizable reduction
(1)
representation preserving
(1)
unified pac learning
(1)
level-constrained (l+1)-branching dimension
(1)
level-constrained (l+1)-littlestone dimension
(1)
list transductive online learning
(1)
minimax number of mistakes
(1)
instance optimal learning curves
(1)
natarajan littlestone tree
(1)
multi-class classification
(1)
progressive littlestone tree
(1)
tsybakov noise
(1)
Papers
A Trichotomy for List Transductive Online Learning
ICML 2025
For Universal Multiclass Online Learning, Bandit Feedback and Full Supervision are Equivalent
ALT 2025
Representation Preserving Multiclass Agnostic to Realizable Reduction
ICML 2025
Universal Rates for Multiclass Learning with Bandit Feedback
COLT 2025