Threshold Policies with Tight Guarantees for Online Selection with Convex Costs.

Xiaoqi TanSiyuan YuRaouf BoutabaAlberto Leon-Garcia
Published in: CoRR (2023)
Keyphrases
  • online learning
  • real time
  • lower bound
  • search costs
  • worst case
  • selection algorithm
  • total cost
  • globally optimal
  • upper bound
  • optimal policy
  • multistage
  • convex hull
  • online environment