New Finite Blocklength Converses for Asymmetric Multiple Access Channels via Linear Programming

This paper presents a systematic method to synthesize new finite blocklength converses for the channel coding of asymmetric multiple access channels (A-MAC) from point-to-point converses, by employing the linear programming (LP) based framework in [1]. A direct synthesis yields a converse that extends the Polyanskiy-Poor-Verdú metaconverse to A-MAC. Employing a more sophisticated non-linear synthesis, we derive a new, code-independent converse that is asymptotically tight.

[1]  Ankur A. Kulkarni,et al.  Linear Programming-Based Converses for Finite Blocklength Lossy Joint Source-Channel Coding , 2016, IEEE Transactions on Information Theory.

[2]  Pierre Moulin,et al.  A new metaconverse and outer region for finite-blocklength MACs , 2013, 2013 Information Theory and Applications Workshop (ITA).

[3]  H. Vincent Poor,et al.  Channel Coding Rate in the Finite Blocklength Regime , 2010, IEEE Transactions on Information Theory.

[4]  Meir Feder,et al.  On the calculation of the minimax-converse of the channel coding problem , 2015, 2017 IEEE International Symposium on Information Theory (ISIT).

[5]  William Matthews,et al.  A Linear Program for the Finite Block Length Converse of Polyanskiy–Poor–Verdú Via Nonsignaling Codes , 2011, IEEE Transactions on Information Theory.

[6]  Pierre Moulin,et al.  Finite blocklength coding for multiple access channels , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.

[7]  Vincent Y. F. Tan,et al.  Second-order asymptotics for the discrete memoryless MAC with degraded message sets , 2014, 2015 IEEE International Symposium on Information Theory (ISIT).

[8]  Sergio Verdú,et al.  Non-asymptotic achievability bounds in multiuser information theory , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).