Rate-distortion functions of non-stationary Markoff chains and their block-independent approximations
Mukul Agarwal

TL;DR
This paper proves that the normalized rate-distortion functions of block-independent approximations of irreducible, aperiodic Markov chains converge to a limit independent of initial distribution, matching the chain's rate-distortion function.
Contribution
It establishes the independence of the limit of normalized rate-distortion functions from initial distributions for certain Markov chains.
Findings
Limit of normalized rate-distortion functions is independent of initial distribution.
The limit equals the rate-distortion function of the original Markov chain.
Results apply to irreducible, aperiodic Markov chains.
Abstract
It is proved that the limit of the normalized rate-distortion functions of block independent approximations of an irreducible, aperiodic Markoff chain is independent of the initial distribution of the Markoff chain and thus, is also equal to the rate-distortion function of the Markoff chain.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
