CMTRL recovers a shared low-rank feature matrix for T constrained linear bandit tasks in d dimensions using Safe-AltGDmin and provides regret and sample complexity bounds.
Improved algorithms for conservative exploration in bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Task Representation Learning for Conservative Linear Bandits
CMTRL recovers a shared low-rank feature matrix for T constrained linear bandit tasks in d dimensions using Safe-AltGDmin and provides regret and sample complexity bounds.