A new 'Local Anti-Concentration' condition on context distributions lets the pure-greedy linear contextual bandit algorithm achieve O(poly log T) expected regret for distributions beyond Gaussian and uniform, including Laplace, exponential, and truncated heavy-tailed laws.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
A new 'Local Anti-Concentration' condition on context distributions lets the pure-greedy linear contextual bandit algorithm achieve O(poly log T) expected regret for distributions beyond Gaussian and uniform, including Laplace, exponential, and truncated heavy-tailed laws.