Login / Signup

Online Learning of Time-Varying Unbalanced Networks in Non-Convex Environments: A Multi-Armed Bandit Approach.

Olusola Tolulope Odeyomi
Published in: IEEE Access (2023)
Keyphrases
  • online learning
  • multi armed bandit
  • regret bounds
  • e learning
  • network structure
  • multi armed bandits
  • convex optimization
  • online convex optimization
  • objective function
  • active learning