vix.ing · top · new · best · stats · spec

Real numbers, data science and chaos: How to fit any dataset with a single parameter

2019/04/28 by Laurent Boué, Boué, Laurent · 7 voices · 1 citation
Computer Science · Economics, Econometrics and Finance · #Time Series Analysis and Forecasting #Complex Systems and Time Series Analysis #Computational Physics and Python Applications

paper · pdf · doi:10.48550/arxiv.1904.12320

Abstract

We show how any dataset of any modality (time-series, images, sound...) can be approximated by a well-behaved (continuous, differentiable...) scalar function with a single real-valued parameter. Building upon elementary concepts from chaos theory, we adopt a pedagogical approach demonstrating how to adjust this parameter in order to achieve arbitrary precision fit to all samples of the data. Targeting an audience of data scientists with a taste for the curious and unusual, the results presented here expand on previous similar observations regarding expressiveness power and generalization of machine learning models.

Cited by

Discussions

Related