Tight Regret and Complexity Bounds for Thompson Sampling via Langevin Monte Carlo.
Tom HuixMatthew ZhangAlain DurmusPublished in: AISTATS (2023)
Keyphrases
- monte carlo
- complexity bounds
- worst case
- lower bound
- upper bound
- adaptive sampling
- importance sampling
- monte carlo simulation
- markov chain
- np hard
- monte carlo methods
- particle filter
- sample size
- variance reduction
- point processes
- matrix inversion
- markov chain monte carlo
- computational complexity
- game tree
- monte carlo tree search
- markovian decision
- temporal difference
- search space