Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!

Niels Bruun Ipsen, Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

49 Downloads (Pure)


How does missing data affect our ability to learn signal structures? It has been shown that learning signal structure in terms of principal components is dependent on the ratio of sample size and dimensionality and that a critical number of observations is needed before learning starts (Biehl and Mietzner, 1993). Here we generalize this analysis to include missing data. Probabilistic principal component analysis is regularly used for estimating signal structures in datasets with missing data. Our analytic result suggests that the effect of missing data is to effectively reduce signal-to-noise ratio rather than - as generally believed - to reduce sample size. The theory predicts a phase transition in the learning curves and this is indeed found both in simulation data and in real datasets.
Original languageEnglish
Title of host publicationProceedings of Machine Learning Research
PublisherInternational Machine Learning Society (IMLS)
Publication date2019
ISBN (Print)9781510886988
Publication statusPublished - 2019
Event36th International Conference on Machine Learning - Long Beach Convention Center, Long Beach, United States
Duration: 10 Jun 201915 Jun 2019
Conference number: 36


Conference36th International Conference on Machine Learning
LocationLong Beach Convention Center
Country/TerritoryUnited States
CityLong Beach


Dive into the research topics of 'Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!'. Together they form a unique fingerprint.

Cite this