Improved Regret Bounds for Bandit Combinatorial Optimization.
Shinji ItoDaisuke HatanoHanna SumitaKei TakemuraTakuro FukunagaNaonori KakimuraKen-ichi KawarabayashiPublished in: NeurIPS (2019)
Keyphrases
- combinatorial optimization
- regret bounds
- multi armed bandit
- combinatorial optimization problems
- simulated annealing
- metaheuristic
- traveling salesman problem
- lower bound
- optimization problems
- online learning
- linear regression
- upper bound
- evolutionary algorithm
- multi objective
- dynamic programming
- cost function
- quadratic assignment problem