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
- How to fit any dataset with a single parameter [hn, 217 points, 146 comments]
- Real numbers, data science and chaos: How to fit any dataset with a single parameter [lobsters, 4 points, 0 comments]
- Data science and chaos: How to fit any dataset with a single parameter [hn, 2 points, 0 comments]
- I posted this a while ago on the bird site (where I initially encountered this paper); putting it on the record here as well. Still trying to get my head around this. Putting chaos to work to fit an a [bsky, 2 points, 0 comments]
- How to fit any dataset with a single parameter [hn, 1 points, 0 comments]
- How to approximate any dataset with a single parameter [pdf] [hn, 1 points, 0 comments]
- @safest_integer And you can actually do it with just one parameter! https://arxiv.org/abs/1904.12320 https://github.com/eliocamp/spfit [bsky, 0 points, 1 comments]
Related