no code implementations • 20 Dec 2023 • Prune Inzerilli, Vladimir Kostic, Karim Lounici, Pietro Novelli, Massimiliano Pontil
We study the evolution of distributions under the action of an ergodic dynamical system, which may be stochastic in nature.
1 code implementation • 19 Jul 2023 • Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics.
no code implementations • 30 May 2022 • Leonardo Cella, Karim Lounici, Massimiliano Pontil
We aim to leverage this information in order to learn a new downstream bandit task, which shares the same representation.
no code implementations • 9 May 2022 • Katia Meziani, Karim Lounici, Benjamin Riu
AdaCap is the combination of two novel ingredients, the Muddling labels for Regularization (MLR) loss and the Tikhonov operator training scheme.
no code implementations • 21 Feb 2022 • Leonardo Cella, Karim Lounici, Grégoire Pacreau, Massimiliano Pontil
We study the problem of transfer-learning in the setting of stochastic linear bandit tasks.
1 code implementation • 8 Jun 2021 • Karim Lounici, Katia Meziani, Benjamin Riu
Deep Learning (DL) is considered the state-of-the-art in computer vision, speech recognition and natural language processing.
no code implementations • 17 Feb 2021 • Karim Lounici, Katia Meziani, Benjamin Riu
The main goal of this paper is to introduce a novel approach to achieve generalization without any data splitting, which is based on a new risk measure which directly quantifies a model's tendency to overfit.
1 code implementation • 11 Jun 2020 • Karim Lounici, Katia Meziani, Benjamin Riu
We observe in our experiments a significantly smaller runtime for our methods as compared to benchmark methods for equivalent prediction score.
no code implementations • 28 Jun 2019 • Laurent Dragoni, Rémi Flamary, Karim Lounici, Patricia Reynaud-Bouret
Spike sorting is a fundamental preprocessing step in neuroscience that is central to access simultaneous but distinct neuronal activities and therefore to better understand the animal or even human brain.
no code implementations • 24 May 2019 • Rémi Flamary, Karim Lounici, André Ferrari
This article investigates the quality of the estimator of the linear Monge mapping between distributions.
no code implementations • 29 Nov 2010 • Vladimir Koltchinskii, Alexandre B. Tsybakov, Karim Lounici
We show that the obtained rates are optimal up to logarithmic factors in a minimax sense and also derive, for any fixed matrix $A_0$, a non-minimax lower bound on the rate of convergence of our estimator, which coincides with the upper bound up to a constant factor.