pith. sign in

arxiv: 1712.06509 · v2 · pith:MYVJJ6PAnew · submitted 2017-12-18 · 🧮 math.PR

Semi-groups of stochastic gradient descent and online principal component analysis: properties and diffusion approximations

classification 🧮 math.PR
keywords propertiesonlinesemigroupsstochasticalgorithmsanalysiscomponentdescent
0
0 comments X
read the original abstract

We study the Markov semigroups for two important algorithms from machine learning: stochastic gradient descent (SGD) and online principal component analysis (PCA). We investigate the effects of small jumps on the properties of the semi-groups. Properties including regularity preserving, $L^{\infty}$ contraction are discussed. These semigroups are the dual of the semigroups for evolution of probability, while the latter are $L^{1}$ contracting and positivity preserving. Using these properties, we show that stochastic differential equations (SDEs) in $\mathbb{R}^d$ (on the sphere $\mathbb{S}^{d-1}$) can be used to approximate SGD (online PCA) weakly. These SDEs may be used to provide some insights of the behaviors of these algorithms.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.