Statistical Rejection Sampling Improves Preference Optimization.
Tianqi LiuYao ZhaoRishabh JoshiMisha KhalmanMohammad SalehPeter J. LiuJialu LiuPublished in: CoRR (2023)
Keyphrases
- optimization problems
- discrete optimization
- global optimization
- hypothesis testing
- information theoretic
- statistical analysis
- adaptive sampling
- random sampling
- data driven
- statistical models
- statistical tests
- decision making
- learning algorithm
- sampling strategy
- optimization algorithm
- monte carlo
- combinatorial optimization
- statistical methods
- multi agent
- optimization methods
- genetic algorithm
- real time