In 2010, Joseph Salmon finished his PHD in Statistics under the supervision of Dominique Picard and Erwan Le Pennec at the Laboratoire de Probabilités et de Modélisation Aléatoire (LPMA ) in Université Paris Diderot.
His thesis is about the denoising of digital images combining patch-based method and statistical aggregation. Salmon is especially interested in topics as: aggregation of estimators, Patch based denoising methods, Non-parametric regression and On-line learning.
From 2011 to the end of 2012, Joseph Salmon was a Post Doctoral Associate at Duke university working with Rebecca Willett in the Network and Imaging Science Laboratory (NISLab) . During this period, he also started lecturing and is sharing his knowledge since 2013 at TELECOM ParisTech.
- Mandatory Critical Points of 2D Uncertain Scalar Fields,
D. Guenther, J. Salmon, J. Tierny, Computer Graphics Forum, aug 2014
- Reconstruction Stable par Régularisation Sécomposable Analyse.,
J. Fadili, G. Peyré, S. Vaiter, Ch.-a. Deledalle, J. Salmon, GRETSI, sep 2013
- Stable Recovery with Analysis Decomposable Priors,
J. Fadili, G. Peyré, S. Vaiter, Ch.-a. Deledalle, J. Salmon, SampTA, jul 2013
- Learning Heteroscedastic Models By Convex Programming Under Group Sparsity ,
A. Dalalyan, M. Hebiri, K. Meziani, J. Salmon, ICML, jun 2013
More info: josephsalmon.eu