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.
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.