Quantization Efficiency as a Function of Manifold Entropy Sean

Read full text Summarise with VIRAT
Authors: sean kingsland
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper introduces the Topological Lock Protocol, a training paradigm that reframes neural network quantization as structured discretization over physically constrained state spaces. By embedding quantization-aware training within physics-governed simulation environments, models converge toward low-entropy manifolds — enabling aggressive low-bit quantization with minimal performance degradation. The work presents a theoretical framework linking manifold entropy to quantization error, and describes a recursive simulation-model coupling loop where the model accelerates simulation and simulation in turn generates higher-quality training data. Applications include edge AI, robotics, and simulation acceleration.

Fields of Study & Subjects

Advanced Neural Network Applications Low-power high-performance VLSI design Neural Networks and Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
25 March 2026
Language
EN
Document type
Preprint