Influence of sampling on the convergence rates of greedy algorithms for parameter-dependent random variables.
Mohamed-Raed BlelVirginie EhrlacherTony LelièvrePublished in: CoRR (2021)
Keyphrases
- random variables
- greedy algorithms
- convergence rate
- greedy algorithm
- independent and identically distributed
- stopping criterion
- graphical models
- probability distribution
- statistically independent
- parameter space
- learning rate
- bayesian networks
- conditional independence
- stochastic optimization problems
- latent variables
- distribution function
- joint distribution
- conditional probabilities
- lead time
- knapsack problem
- normal distribution
- conditionally independent
- random sampling
- marginal distributions
- primal dual
- low memory requirements
- random vectors
- identically distributed
- worst case
- computational complexity