10.6k citations
- Laboratoire Traitement et Communication de l’InformationFR516 papers
- Centre National de la Recherche ScientifiqueFR357 papers
- ParisTechFR221 papers
- Université Paris-SudFR118 papers
- Institut Polytechnique de ParisFR115 papers
- Université Paris-SaclayFR114 papers
- University of California, BerkeleyUS114 papers
- University of TorontoCA110 papers
- Imperial College LondonGB109 papers
- Sapienza University of RomeIT109 papers
- University of CambridgeGB109 papers
- California Institute of TechnologyUS108 papers
9 papers · 2 filters
Learning Sparse Neural Networks via Sensitivity-Driven Regularization
Enzo Tartaglione, Skjalg Lepsøy, Attilio Fiandrotti +1
The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by s…
Weighted Spectral Embedding of Graphs
Thomas Bonald, Alexandre Hollocou, Marc Lelarge
We present a novel spectral embedding of graphs that incorporates weights assigned to the nodes, quantifying their relative importance. This spectral embedding is based on the firs…
Bounds on the Approximation Power of Feedforward Neural Networks
Mohammad Mehrabi, Aslan Tchamkerten, Mansoor I. Yousefi
The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are establis…
A Unified Framework for Training Neural Networks
Hadi Ghauch, Hossein Shokri-Ghadikolaei, Carlo Fischione +1
The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general sett…
Semi-Supervised Learning with GANs: Revisiting Manifold Regularization
Bruno Lecouat, Chuan-Sheng Foo, Houssam Zenati +1
GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplaci…
Infinite-Task Learning with RKHSs
Romain Brault, Alex Lambert, Zoltán Szabó +2
Machine learning has witnessed tremendous success in solving tasks depending on a single hyperparameter. When considering simultaneously a finite number of tasks, multi-task learni…