Alexander Kozachinskiy
8 papers · 2023–2025 · 6 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(12)
🏆
Grand Slam
Top co-authors
Research topics
Keywords
littlestone dimension
(3)
hard attention
(2)
mistake bound
(2)
pac learning
(1)
weisfeiler-lehman test
(1)
first-order logic
(1)
transformer
(1)
expert advice
(1)
hypothesis class
(1)
formal language
(1)
graph isomorphism
(1)
algorithm analysis
(1)
approval voting
(1)
activation function
(1)
point cloud
(1)
proper learning
(1)
transformer encoder
(1)
pac learnability
(1)
circuit complexity
(1)
sample complexity
(1)
Papers
Effective Littlestone dimension
ALT 2025
Ehrenfeucht-Haussler Rank and Chain of Thought
ICML 2025
Optimal Bounds for Dissatisfaction in Perpetual Voting
AAAI 2025
Logical Languages Accepted by Transformer Encoders with Hard Attention
ICLR 2024
On dimensionality of feature vectors in MPNNs
ICML 2024
Simple online learning with consistent oracle
COLT 2024
Find a witness or shatter: the landscape of computable PAC learning.
COLT 2023
Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points
NeurIPS 2023