Hierarchical interval trees with lazy insertion and vector-encoded rewards enable efficient proportional sampling under σ-smoothed adversaries, with tight O(√(σT)) depth and sublinear-regret online learning.
Mahoney , title =
1 Pith paper cite this work, alongside 566 external citations. Polarity classification is still indexing.
1
Pith paper citing it
566
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Efficient Online Proportional Sampling with Applications to Smoothed Online Learning
Hierarchical interval trees with lazy insertion and vector-encoded rewards enable efficient proportional sampling under σ-smoothed adversaries, with tight O(√(σT)) depth and sublinear-regret online learning.