C. Cheng, G. Nührenberg, C. Huang, and H. Ruess. (2017)cite arxiv:1710.03107Comment: Version 2: add proofs for hardness of PTAS approximability, remove experiments on randomized examples and some not-so-important optimizations.
A. Rozsa, M. Gunther, and T. Boult. (2016)cite arxiv:1612.00138Comment: Accepted to the IEEE Winter Conference on Applications of Computer Vision (WACV), 2018.
D. Soudry, E. Hoffer, M. Nacson, S. Gunasekar, and N. Srebro. (2017)cite arxiv:1710.10345Comment: Journal version (previous version appeared as conference paper in ICLR ). Main improvements: We proved measure zero case for main theorem (with implication for the rates), and the multi-class case. Both were not covered in previous version.