-
The Experience
-
About Stanford GSB
About Our Degree Programs
-
-
The Programs
-
Full-Time Degree Programs
Non-Degree & Certificate Programs
-
-
Faculty & Research
-
Faculty
Faculty Research
Research Hub
Centers & Institutes
-
-
Insights
-
Topics
-
-
Alumni
-
Welcome, Alumni
-
-
Events
-
Admission Events & Information Sessions
-
Survey Bandits with Regret Guarantees
Survey Bandits with Regret Guarantees
February 23,2020Working Paper No. 3902
We consider a variant of the contextual bandit problem. In standard contextual bandits, when a user arrives we get the user’s complete feature vector and then assign a treatment (arm) to that user. In a number of applications (like health care), collecting features from users can be costly. To address this issue, we propose algorithms that avoid needless feature collection while maintaining strong regret guarantees.