A Tight Upper Bound for the Third-Order Asymptotics for Most Discrete Memoryless Channels
Marco Tomamichel, Vincent Y. F. Tan

TL;DR
This paper establishes a precise third-order upper bound on the epsilon-error capacity for discrete memoryless channels, matching known lower bounds and clarifying the asymptotic behavior depending on the channel's dispersion.
Contribution
It provides a tight third-order upper bound for the epsilon-error capacity of discrete memoryless channels, extending previous second-order results.
Findings
Upper bound matches the lower bound for channels with positive dispersion.
For channels with vanishing dispersion, the capacity is tightly bounded by n times the capacity plus a constant.
The third-order term does not exceed 1/2 log n + O(1) for channels with positive epsilon-dispersion.
Abstract
This paper shows that the logarithm of the epsilon-error capacity (average error probability) for n uses of a discrete memoryless channel is upper bounded by the normal approximation plus a third-order term that does not exceed 1/2 log n + O(1) if the epsilon-dispersion of the channel is positive. This matches a lower bound by Y. Polyanskiy (2010) for discrete memoryless channels with positive reverse dispersion. If the epsilon-dispersion vanishes, the logarithm of the epsilon-error capacity is upper bounded by the n times the capacity plus a constant term except for a small class of DMCs and epsilon >= 1/2.
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.
