T. Blumensath and M. E. Davies, Gradient pursuits, IEEE Transactions on Signal Processing, vol.56, issue.6, pp.2370-2382, 2008.

S. Boyd and L. Vandenberghe, Convex optimization, 2004.

S. Bubeck, Convex optimization: Algorithms and complexity. Foundations and Trends R in Machine Learning, vol.8, pp.231-357, 2015.

D. L. Scott-shaobing-chen, M. Donoho, and . Saunders, Atomic decomposition by basis pursuit, SIAM review, vol.43, issue.1, pp.129-159, 2001.

G. Davis, S. Mallat, and M. Avellaneda, Adaptive greedy approximations. Constructive approximation, vol.13, pp.57-98, 1997.

M. Frank and P. Wolfe, An algorithm for quadratic programming, Naval Research Logistics (NRL), vol.3, issue.1-2, pp.95-110, 1956.

R. Gribonval and P. Vandergheynst, On the exponential convergence of matching pursuits in quasi-incoherent dictionaries, IEEE Transactions on Information Theory, vol.52, issue.1, pp.255-261, 2006.
URL : https://hal.archives-ouvertes.fr/inria-00544945

J. Guélat and P. Marcotte, Some comments on wolfe's 'away step, Mathematical Programming, vol.35, pp.110-119, 1986.

F. Locatello, R. Khanna, M. Tschannen, and M. Jaggi, A unified optimization view on generalized matching pursuit and frank-wolfe, Artificial Intelligence and Statistics, pp.860-868, 2017.

G. Stéphane, Z. Mallat, and . Zhang, Matching pursuits with time-frequency dictionaries, IEEE Transactions on signal processing, vol.41, issue.12, pp.3397-3415, 1993.

A. Miller, Subset selection in regression, 2002.

Y. Chandra-pati, R. Rezaiifar, and P. Krishnaprasad, Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. Signals, Systems and Computers, Conference Record of The Twenty-Seventh Asilomar Conference on, pp.40-44, 1993.

D. Bhaskar, K. Rao, and . Kreutz-delgado, An affine scaling methodology for best basis selection, IEEE Transactions on signal processing, vol.47, issue.1, pp.187-200, 1999.

V. N. Temlyakov, Nonlinear methods of approximation, Foundations of Computational Mathematics, vol.3, issue.1, 2003.

V. N. Temlyakov, Greedy approximation, vol.20, 2011.
DOI : 10.1017/cbo9780511762291

R. Tibshirani, Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society. Series B (Methodological), pp.267-288, 1996.
DOI : 10.1111/j.2517-6161.1996.tb02080.x

J. A. Tropp, Greed is good: Algorithmic results for sparse approximation, IEEE Transactions on Information theory, vol.50, issue.10, pp.2231-2242, 2004.
DOI : 10.1109/tit.2004.834793

URL : http://users.cms.caltech.edu/~jtropp/papers/Tro04-Greed-Good.pdf

J. A. Tropp, Just relax: Convex programming methods for identifying sparse signals in noise, IEEE transactions on information theory, vol.52, issue.3, pp.1030-1051, 2006.
DOI : 10.1109/tit.2005.864420

URL : http://www.acm.caltech.edu/%7Ejtropp/papers/Tro06-Just-Relax.pdf

, She is now a Ph.D. student at the same university. Her research focuses on active learning and she is also interested in some signal processing problems, Sc. degree in computer science in 2016 and a M.Sc. degree in computer science in 2018, both from Aix-Marseille university

, within the QARMA team at Laboratoire d'Informatique et Systèmes. His research interests focus on machine learning and audio signal processing, including sparse representations, sound modeling, inpainting, source separation, 2003 and received the M.Sc. degree in Acoustics, Signal Processing and Computer Science Applied to Music (ATIAM) at Ircam, France, 2004.

, France since 2016 and part-time researcher at Criteo since 2018. He received the Ph.D. degree in Computer Science from Université Paris 6 in 2003, and his HabilitationàHabilitation`Habilitationà Diriger des Recherches in Computer Science from AMU in 2010. His research focuses on statistical and algorithmic aspects of machine learning with a focus on theoretical issues

, She obtained a Ph.D in applied mathematics at Princeton University in 2005. She then worked as a postdoctoral researcher at Aix-Marseille University for a year. Since 2006, she is working as a research fellow for the Centre National de Recherche Scientifique (CNRS). She started at the computer science and signal processing lab, Sandrine Anthoine received a B.Sc. and M.Sc. in mathematics from ENS Cachan, 1999.