Abstract | ||
---|---|---|
This paper studies least-square regression penalized with partly smooth convex regularizers. This class of penalty functions is very large and versatile, and allows to promote solutions conforming to some notion of low complexity. Indeed, such penalties/regularizers force the corresponding solutions to belong to a low-dimensional manifold (the so-called model), which remains stable when the argume... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIT.2017.2713822 | IEEE Transactions on Information Theory |
Keywords | Field | DocType |
Manifolds,Convex functions,Inverse problems,Imaging,Mathematical model,Buildings,Matrix decomposition | Mathematical optimization,Regression,Model selection,Regular polygon,Design matrix,Regularization (mathematics),Mathematics,Manifold,Perturbation (astronomy),Estimator | Journal |
Volume | Issue | ISSN |
64 | 3 | 0018-9448 |
Citations | PageRank | References |
10 | 0.59 | 19 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Samuel Vaiter | 1 | 50 | 8.39 |
Gabriel Peyré | 2 | 1195 | 79.60 |
Jalal Fadili | 3 | 1184 | 80.08 |