Multitask Learning and Bandits via Robust Statistics

Decision makers often simultaneously face many related but heterogeneous learning problems. For instance, a large retailer may wish to learn product demand at different stores to solve pricing or inventory problems, making it desirable to learn jointly for stores serving similar customers; alternatively, a hospital network may wish to learn patient risk at different providers to allocate personalized interventions, making it desirable to learn jointly for hospitals serving similar patient populations. Motivated by real data sets, we study a natural setting where the unknown parameter in each learning instance can be decomposed into a shared global parameter plus a sparse instance-specific term. We propose a novel two-stage multitask learning estimator that exploits this structure in a sample-efficient way, using a unique combination of robust statistics (to learn across similar instances) and LASSO regression (to debias the results). Our estimator yields improved sample complexity bounds in the feature dimension d relative to commonly employed estimators; this improvement is exponential for “data-poor” instances, which benefit the most from multitask learning. We illustrate the utility of these results for online learning by embedding our multitask estimator within simultaneous contextual bandit algorithms. We specify a dynamic calibration of our estimator to appropriately balance the bias-variance trade-off over time, improving the resulting regret bounds in the context dimension d. Finally, we illustrate the value of our approach on synthetic and real data sets. This paper was accepted by J. George Shanthikumar, data science. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2022.00490 .

• 저널Management Science · 71(9) · 7752–7773
• 토픽Advanced Bandit Algorithms Research · Management Science and Operations Research
• DOI10.1287/mnsc.2022.00490
• 저자Kan Xu, Hamsa Bastani