M. Bhargava, and A. Shankar. (2010)cite arxiv:1006.1002Comment: Proofs have been considerably streamlined, and a number of clarifying details have been added; 36 pages.
R. Bondesan, and A. Lamacraft. (2019)cite arxiv:1906.04645Comment: 8 pages, 5 figures. Presented at the ICML 2019 Workshop on Theoretical Physics for Deep Learning.
S. Chatterjee. (2005)cite arxiv:math/0510424Comment: This will appear as a theorem in Robert Adler's new book with Jonathan Taylor on gaussian processes; will not be submitted to any journal in its present form.