A Sharp Memory-Regret Trade-off for Multi-Pass Streaming Bandits.
Arpit AgarwalSanjeev KhannaPrathamesh PatilPublished in: COLT (2022)
Keyphrases
- trade off
- regret bounds
- online learning
- memory requirements
- multi armed bandit problems
- multi armed bandits
- data streams
- main memory
- multi armed bandit
- lower bound
- binary classification
- memory usage
- weighted majority
- real time
- worst case
- loss function
- database
- computing power
- memory space
- data structure
- stochastic systems
- database systems