Deep neural networks have been used widely to learn the latent structure of datasets, across
modalities such as images, shapes, and audio signals. However, existing models are …

We present a novel mechanism to improve the accuracy of the recently-introduced class of
graph random features (GRFs). Our method induces negative correlations between the …

We present a novel quasi-Monte Carlo mechanism to improve graph-based sampling,
coined repelling random walks. By inducing correlations between the trajectories of an …

In natural language processing (NLP), document classification is an important task that
relies on the proper thematic representation of the documents. Gaussian mixture-based …

On a compact Riemannian manifold $ M, $ we show that the Riemannian distance function $
d (x, y) $ can be explicitly reconstructed from suitable asymptotics of the expected signature …