The MLA-UCB algorithm uses ML-generated surrogate rewards from auxiliary data to provably lower cumulative regret in multi-armed bandits, achieving asymptotic optimality under joint Gaussian assumptions without requiring knowledge of the true-surrogate covariance.
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying learning signal may be different between these two data sources. Theoretically, we state and prove no-regret algorithms for learning that is robust to misaligned cost distributions between the two sources. Empirically, we evaluate some of these algorithms on a large selection of datasets, showing that our approach is both feasible and helpful in practice.
verdicts
UNVERDICTED 2representative citing papers
Identifiable latent bandits apply nonlinear ICA to observational data to recover representations sufficient for inferring optimal actions in new instances, shortening exploration time.
citing papers explorer
-
Multi-Armed Bandits With Machine Learning-Generated Surrogate Rewards
The MLA-UCB algorithm uses ML-generated surrogate rewards from auxiliary data to provably lower cumulative regret in multi-armed bandits, achieving asymptotic optimality under joint Gaussian assumptions without requiring knowledge of the true-surrogate covariance.
-
Identifiable Latent Bandits: Leveraging observational data for personalized decision-making
Identifiable latent bandits apply nonlinear ICA to observational data to recover representations sufficient for inferring optimal actions in new instances, shortening exploration time.