Papers

The Theory and Algorithm of Ergodic Inference

Y Zhang - arXiv preprint arXiv:1811.07192, 2018 - arxiv.org
Computer Science paper cs.LG Suggest

… Monte Carlo method is the most popular simulation based inference technique in probabilistic modelling. For example, to fit a probabilistic model π by maximum likelihood estimation, it …

Cited by Link to paper

BibTeX

@article{1811.07192v1,
Author        = {Yichuan Zhang},
Title         = {The Theory and Algorithm of Ergodic Inference},
Eprint        = {1811.07192v1},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.LG},
Abstract      = {Approximate inference algorithm is one of the fundamental research fields in
machine learning. The two dominant theoretical inference frameworks in machine
learning are variational inference (VI) and Markov chain Monte Carlo (MCMC).
However, because of the fundamental limitation in the theory, it is very
challenging to improve existing VI and MCMC methods on both the computational
scalability and statistical efficiency. To overcome this obstacle, we propose a
new theoretical inference framework called ergodic Inference based on the
fundamental property of ergodic transformations. The key contribution of this
work is to establish the theoretical foundation of ergodic inference for the
development of practical algorithms in future work.},
Year          = {2018},
Month         = {Nov},
Url           = {http://arxiv.org/abs/1811.07192v1},
File          = {1811.07192v1.pdf}
}

Share