Universal A Posteriori Metrics Game
Emmanuel Abbe, Rethnakaran Pulikkoonattu

TL;DR
This paper investigates universal a posteriori metrics for binary channels, demonstrating that a simple decoder with two metrics can match the performance of an optimal decoder across all channels, achieving at least 94.2% of the capacity.
Contribution
It introduces a universal generalized linear decoder with two metrics that attains the same performance as the optimal decoder for all binary channels.
Findings
Two metrics suffice to match optimal decoder performance.
The universal decoder achieves at least 94.2% of the capacity.
Existence of a decoder that is both generalized linear and universally effective.
Abstract
Over binary input channels, uniform distribution is a universal prior, in the sense that it allows to maximize the worst case mutual information over all binary input channels, ensuring at least 94.2% of the capacity. In this paper, we address a similar question, but with respect to a universal generalized linear decoder. We look for the best collection of finitely many a posteriori metrics, to maximize the worst case mismatched mutual information achieved by decoding with these metrics (instead of an optimal decoder such as the Maximum Likelihood (ML) tuned to the true channel). It is shown that for binary input and output channels, two metrics suffice to actually achieve the same performance as an optimal decoder. In particular, this implies that there exist a decoder which is generalized linear and achieves at least 94.2% of the compound capacity on any compound set, without the…
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.
Taxonomy
TopicsWireless Communication Security Techniques · Error Correcting Code Techniques · Cooperative Communication and Network Coding
