[1904.12320] Real numbers, data science and chaos: How to fit any dataset with a single parameter

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.

Real numbers, data science and chaos: How to fit any dataset with a single parameter Laurent Boué SAP Labs arXiv:1904.12320v1 [cs.LG] 28 Apr 2019 Abstract We show how any dataset of any modality…

related reading

• Scaling Laws, Carefully | Lil'Loglilianweng.github.io
• Datacurve | The data engine for frontier AIdatacurve.ai
• The “it” in AI models is the dataset. — Non_Intnonint.com
• Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetsmathai-iclr.github.io
• The Little Book of Deep Learningfleuret.org
• Zipfian grokking | Jasper Gilleyjagilley.github.io
• deeplearningbook.org/contents/ml.htmldeeplearningbook.org
• A Course in Machine Learningciml.info
• The generalization phase diagram — LessWronglesswrong.com
• What's new | Updates on my research and expository papers, discussion of open problems, and other maths-related topics. By Terence Taoterrytao.wordpress.com
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugesarxiv.org
• arxiv.org/pdf/1805.08522arxiv.org