Author:
Thorpe Matthew,Theil Florian
Abstract
AbstractThe Ginzburg–Landau functional is a phase transition model which is suitable for classification type problems. We study the asymptotics of a sequence of Ginzburg–Landau functionals with anisotropic interaction potentials on point clouds Ψnwherendenotes the number data points. In particular, we show the limiting problem, in the sense of Γ-convergence, is related to the total variation norm restricted to functions taking binary values, which can be understood as a surface energy. We generalize the result known for isotropic interaction potentials to the anisotropic case and add a result concerning the rate of convergence.
Publisher
Cambridge University Press (CUP)
Reference50 articles.
1. Comparing community structure identification
2. The $$L^\infty $$ L ∞ optimal transport: infinite cyclical monotonicity and the existence of optimal transport maps
3. X. Zhou and M. Belkin . Semi-supervised learning by higher order regularization. In International Conference on Artificial Intelligence and Statistics, pp. 892–900 (2011).
4. Detecting changes in nonisotropic images
5. A. El Alaoui , X. Cheng , A. Ramdas , M. J. Wainwright and M. I. Jordan . Asymptotic behavior of ℓ p -based Laplacian regularization in semi-supervised learning. In 29th Annual Conference on Learning Theory, pp. 879–906 (2016).
Cited by
8 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献