Minimax Algorithm for Learning Rotations
[edit]
Proceedings of the 24th Annual Conference on Learning Theory, PMLR 19:821824, 2011.
Abstract
It is unknown what is the most suitable regularization for rotation matrices and how to maintain uncertainty overrotations in an online setting.We propose to address these questions by studying the minimax algorithm for rotations and begin by working out the 2dimensional case.
Related Material



