no code implementations • 17 May 2019 • Emile Richard
We study SGD and Adam for estimating a rank one signal planted in matrix or tensor noise.
no code implementations • NeurIPS 2015 • Emile Richard, Georges A. Goetz, E.J. Chichilnisky
Here, we develop automated classifiers for functional identification of retinal ganglion cells, the output neurons of the retina, based solely on recorded voltage patterns on a large scale array.
no code implementations • NeurIPS 2014 • Yash Deshpande, Andrea Montanari, Emile Richard
We consider a simple model for noisy quadratic observation of an unknown vector $\bvz$.
no code implementations • NeurIPS 2014 • Andrea Montanari, Emile Richard
This is possibly related to a fundamental limitation of computationally tractable estimators for this problem.
no code implementations • NeurIPS 2014 • Emile Richard, Guillaume Obozinski, Jean-Philippe Vert
Based on a new atomic norm, we propose a new convex formulation for sparse matrix factorization problems in which the number of nonzero elements of the factors is assumed fixed and known.
no code implementations • NeurIPS 2012 • Emile Richard, Stephane Gaiffas, Nicolas Vayatis
In the paper, we consider the problem of link prediction in time-evolving graphs.
1 code implementation • 27 Jun 2012 • Emile Richard, Pierre-Andre Savalle, Nicolas Vayatis
The paper introduces a penalized matrix estimation procedure aiming at solutions which are sparse and low-rank at the same time.
no code implementations • NeurIPS 2010 • Emile Richard, Nicolas Baskiotis, Theodoros Evgeniou, Nicolas Vayatis
We consider the problem of discovering links of an evolving undirected graph given a series of past snapshots of that graph.