Stochastic expectation maximization with variance reduction
Expectation-Maximization (EM) is a popular tool for learning latent variable models, but the vanilla batch EM does not scale to large data sets because the whole data set is needed at every E-step. Stochastic Expectation Maximization (sEM) reduces the cost of E-step by stochastic approximation. Howe...
Главные авторы: | Chen, J, Zhu, J, Teh, Y, Zhang, T |
---|---|
Формат: | Conference item |
Опубликовано: |
Massachusetts Institute of Technology Press
2018
|
Схожие документы
-
Non-negative variance component estimation for the partial EIV model by the expectation maximization algorithm
по: Leyang Wang, и др.
Опубликовано: (2020-01-01) -
On the pricing of forward-start variance swaps with stochastic volatility and stochastic interest rate
по: Roslan, Teh Raihana Nazirah
Опубликовано: (2017) -
Pricing variance swaps under stochastic volatility and stochastic interest rate
по: Cao, Jiling, и др.
Опубликовано: (2016) -
Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
по: Vollmer, S, и др.
Опубликовано: (2016) -
Accelerated Stochastic Variance Reduction Gradient Algorithms for Robust Subspace Clustering
по: Hongying Liu, и др.
Опубликовано: (2024-06-01)