A betting loss for bounded regression yields a variance-adaptive generalization bound, improving on first-order bounds that scale with the worst-case proxy f(1-f).
Open problem: First-order regret bounds for contextual bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Second-Order Bounds for [0,1]-Valued Regression via Betting Loss
A betting loss for bounded regression yields a variance-adaptive generalization bound, improving on first-order bounds that scale with the worst-case proxy f(1-f).