no code implementations • 21 Mar 2023 • Fabien Lauer
This paper extends standard results from learning theory with independent data to sequences of dependent data.
no code implementations • 7 Mar 2023 • Fabien Lauer
This paper deals with the scenario approach to robust optimization.
no code implementations • 16 Apr 2019 • Fabien Lauer
This paper proposes a simple approach to derive efficient error bounds for learning multiple components with sparsity-inducing regularization.
no code implementations • 3 Dec 2018 • Khadija Musayeva, Fabien Lauer, Yann Guermeur
This capacity measure is then linked to the metric entropy through the chaining method.
no code implementations • 15 Jun 2018 • Fabien Lauer
This paper deals with robust regression and subspace estimation and more precisely with the problem of minimizing a saturated loss function.
no code implementations • 25 Jul 2017 • Fabien Lauer
For switching regression, the decomposition can be performed directly at the level of the Rademacher complexities, which yields bounds with a linear dependency on the number of modes.
no code implementations • 18 Jul 2017 • Fabien Lauer
The paper provides global optimization algorithms for two particularly difficult nonconvex problems raised by hybrid system identification: switching linear regression and bounded-error estimation.
no code implementations • 23 Oct 2015 • Fabien Lauer
This technical note extends recent results on the computational complexity of globally minimizing the error of piecewise-affine models to the related problem of minimizing the error of switching linear regression models.
no code implementations • 8 Sep 2015 • Fabien Lauer
Previous work showed that a global solution could be obtained for continuous PWA maps with a worst-case complexity exponential in the number of data.
no code implementations • 24 Feb 2014 • Fabien Lauer, Henrik Ohlsson
This paper deals with sparse phase retrieval, i. e., the problem of estimating a vector from quadratic measurements under the assumption that few components are nonzero.
no code implementations • 22 Nov 2013 • Fabien Lauer, Henrik Ohlsson
In particular, we show how these solutions can be recovered from group-sparse solutions of a derived system of linear equations.