Asymptotic optimality of adaptive importance sampling - Archive ouverte HAL
Communication Dans Un Congrès Année : 2018

Asymptotic optimality of adaptive importance sampling

Résumé

Adaptive importance sampling (AIS) uses past samples to update the sampling policy qt. Each stage t is formed with two steps : (i) to explore the space with nt points according to qt and (ii) to exploit the current amount of information to update the sampling policy. The very fundamental question raised in this paper concerns the behavior of empirical sums based on AIS. Without making any assumption on the allocation policy nt, the theory developed involves no restriction on the split of computational resources between the explore (i) and the exploit (ii) step. It is shown that AIS is asymptotically optimal : the asymptotic behavior of AIS is the same as some “oracle” strategy that knows the targeted sampling policy from the beginning. From a practical perspective, weighted AIS is introduced, a new method that allows to forget poor samples from early stages.
Fichier non déposé

Dates et versions

hal-02094838 , version 1 (10-04-2019)

Identifiants

  • HAL Id : hal-02094838 , version 1

Citer

Bernard Delyon, François Portier. Asymptotic optimality of adaptive importance sampling. 32nd Conference on Neural Information Processing Systems (NIPS), Dec 2018, Montréal, Canada. ⟨hal-02094838⟩
60 Consultations
0 Téléchargements

Partager

More