Deep code: representation and learning algorithms for neural networks & their applications to communication codes

Codes are the backbone of modern information age. Codes, composed of encoder and decoder pairs, are the basic mathematical objects that enable reliable communication. Landmark codes include convolutional, Reed-Muller, turbo, LDPC, and polar: each is linear and represents a mathematical breakthrough. Their impact on humanity is huge; each of these codes has been used in global communication standards over the past six decades. On the other hand, designing codes is a challenging task, mostly driven by human ingenuity. Befittingly, historically, the progress in discovery of codes has been sporadic. In this thesis, we present a new paradigm to invent codes via harnessing tools from deep-learning. Our major result is the invention of \emph{KO codes}, a computationally efficient family of deep-learning driven codes that outperform the state-of-the-art RM and polar codes, in the challenging short-to-medium block length regime. The key technical innovation behind KO codes is the design of a novel family of neural architectures inspired by the computation tree of the {\bf K}ronecker {\bf O}peration (KO) central to RM and polar codes. These architectures pave the way for discovery of a much richer class of hitherto unexplored non-linear codes. This design technique can be viewed as an instantiation of the classical neural augmentation principle. In the process, we also study a popular neural network model called Mixture-of-Experts (MoE) that realizes this principle. We provide the first set of consistent and efficient algorithms with global learning guarantees for learning the parameters in a MoE which has been an open problem for more than two decades.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2022

Author dc:creator

• Makkuva, Ashok Vardhan

Contributors dc:contributor

• Viswanath, Pramod
• Hajek, Bruce
• Rayadurgam, Srikant
• Sun, Ruoyu
• Oh, Sewoong

• machine-learning
• LSTM
• GRU
• mixture-of-experts
• deep learning
• KO codes
• channel codes
• error-correcting-codes
• Reed-Muller codes
• Polar codes

Statement dc:rights

• Copyright 2022 Ashok Makkuva

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/116250

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F116250