no code implementations • 7 Jul 2023 • Nicolás García Trillos, Anna Little, Daniel Mckenzie, James M. Murphy
In particular, we show the discrete eigenvalues and eigenvectors converge to their continuum analogues at a dimension-dependent rate, which allows us to interpret the efficacy of discrete spectral clustering using Fermat distances in terms of the resulting continuum limit.
1 code implementation • 30 May 2023 • Leon Bungert, Nicolás García Trillos, Matt Jacobs, Daniel Mckenzie, Đorđe Nikolić, Qingsong Wang
Although deep neural networks have achieved super-human performance on many classification tasks, they often exhibit a worrying lack of robustness towards adversarially generated examples.
1 code implementation • 13 Oct 2022 • Aditya Kumar Akash, Sixu Li, Nicolás García Trillos
In our framework, the fusion occurs in a layer-wise manner and builds on an interpretation of a node in a network as a function of the layer preceding it.
no code implementations • 6 Sep 2022 • Nicolás García Trillos, Ryan Murray, Matthew Thorpe
In the (special) smoothing spline problem one considers a variational problem with a quadratic data fidelity penalty and Laplacian regularisation.
no code implementations • 26 Nov 2021 • Leon Bungert, Nicolás García Trillos, Ryan Murray
We establish an equivalence between a family of adversarial training problems for non-parametric binary classification and a family of regularized risk minimization problems where the regularizer is a nonlocal perimeter functional.
no code implementations • 18 Aug 2021 • Katy Craig, Nicolás García Trillos, Dejan Slepčev
In this work we build a unifying framework to interpolate between density-driven and geometry-based algorithms for data clustering, and specifically, to connect the mean shift algorithm with spectral clustering at discrete and continuum levels.
no code implementations • 8 Aug 2015 • Nicolás García Trillos, Dejan Slepčev
We also show that the discrete clusters obtained via spectral clustering converge towards a continuum partition of the ground truth measure.
no code implementations • 25 Mar 2014 • Nicolás García Trillos, Dejan Slepčev
We consider point clouds obtained as random samples of a measure on a Euclidean domain.