1 code implementation • 1 Sep 2021 • Jacob Leygonie, Mathieu Carrière, Théo Lacombe, Steve Oudot
We introduce a novel gradient descent algorithm extending the well-known Gradient Sampling methodology to the class of stratifiably smooth objective functions, which are defined as locally Lipschitz functions that are smooth on some regular pieces-called the strata-of the ambient Euclidean space.
no code implementations • 10 Jan 2021 • Ka Man Yim, Jacob Leygonie
Since the spectral wavelet signature of a graph is derived from its Laplacian, our framework encodes geometric properties of graphs in their associated persistence diagrams and can be applied to graphs without a priori node attributes.
1 code implementation • 24 Jun 2019 • Jacob Leygonie, Jennifer She, Amjad Almahairi, Sai Rajeswar, Aaron Courville
We show that during training, our generator follows the $W_2$-geodesic between the initial and the target distributions.