Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn about the challenges and solutions in principal component analysis through this mathematics research talk that addresses the 'curse of isotropy' - a critical issue affecting the interpretation of principal components with similar eigenvalues. Explore how rotational variability can impact analysis results and discover a novel approach using probabilistic covariance models parameterized with flags of subspaces. Master the concept of principal subspace analysis as a more reliable alternative to traditional principal components, with demonstrations of its practical applications across various scientific datasets. The presentation, delivered at the Erwin Schrödinger International Institute's Thematic Programme on "Infinite-dimensional Geometry," offers a straightforward methodology that promises improved interpretability in exploratory data analysis.
