We propose a variant of the classical conditional gradient method (CGM) for sparse inverse problems with differentiable measurement models. Such models arise in many practical problems includingâ€¦ (More)

It has been proposed that cumulative somatic mutations contribute to the aging process by disrupting the transcriptional networks that regulate cell structure and function. Experimental support forâ€¦ (More)

This paper provides a theoretical analysis of diffraction-limited superresolution, demonstrating that arbitrarily close point sources can be resolved in ideal situations. Precisely, we assume thatâ€¦ (More)

f-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics and informationâ€¦ (More)

f-divergences are a general class of divergences between probability measures which include as special cases many commonly used divergences in probability, mathematical statistics, and informationâ€¦ (More)

Clustering of data sets is a standard problem in many areas of science and engineering. The method of spectral clustering is based on embedding the data set using a kernel function, and using the topâ€¦ (More)

Author Affiliations Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA Whitehead Institute for Biomedical Research, Cambridge, MA 02142, USA Computational and Systems Biology Program, MIT,â€¦ (More)

We propose a new method to estimate Wasserstein distances and optimal transport plans between two probability distributions from samples in high-dimension. Unlike plug-in rules that simply replaceâ€¦ (More)