Contributed Talk
in
Workshop: Neural Compression: From Information Theory to Applications

Spotlight 3: James Townsend and Iain Murray, Lossless compression with state space models using bits back coding


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.