English

Lossless compression with state space models using bits back coding

Machine Learning 2021-05-05 v3 Artificial Intelligence Information Theory math.IT Machine Learning

Abstract

We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian state space models (LGSSMs) and many more. We provide experimental evidence that our method is effective for small scale models, and discuss its applicability to larger scale settings such as video compression.

Cite

@article{arxiv.2103.10150,
  title  = {Lossless compression with state space models using bits back coding},
  author = {James Townsend and Iain Murray},
  journal= {arXiv preprint arXiv:2103.10150},
  year   = {2021}
}