Online Policy Learning and Inference by Matrix Completion
Making online decisions can be challenging when features are sparse and orthogonal to
historical ones, especially when the optimal policy is learned through collaborative filtering …
historical ones, especially when the optimal policy is learned through collaborative filtering …
Online Learning and Resource Allocation: Algorithms under Non-stationarity
Y Wang, W You, J Jiang - No. This is a working paper, 2024 - papers.ssrn.com
We consider an online stochastic optimization problem with multiple resource constraints
over a finite horizon. In each time period, the decision maker selects an action from a convex …
over a finite horizon. In each time period, the decision maker selects an action from a convex …