LGMLMar 26, 2018

A Common Framework for Natural Gradient and Taylor based Optimisation using Manifold Theory

arXiv:1803.09791v31 citations
Originality Synthesis-oriented
AI Analysis

This work offers a theoretical unification for optimization techniques in machine learning, but it appears incremental as it builds on existing methods without introducing new algorithms.

The authors developed a theoretical framework that connects Taylor approximation-based optimization methods with Natural Gradient (NG) optimization, which is Fisher efficient for probabilistic models, and provided mathematical justification for combining higher-order methods with NG.

This technical report constructs a theoretical framework to relate standard Taylor approximation based optimisation methods with Natural Gradient (NG), a method which is Fisher efficient with probabilistic models. Such a framework will be shown to also provide mathematical justification to combine higher order methods with the method of NG.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes