Alberto Bietti
Alberto Bietti
Bestätigte E-Mail-Adresse bei nyu.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
On the Inductive Bias of Neural Tangent Kernels
A Bietti, J Mairal
Advances in Neural Information Processing Systems (NeurIPS), 2019
482019
Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations
A Bietti, J Mairal
Journal of Machine Learning Research 20 (25), 1-49, 2019
43*2019
A Contextual Bandit Bake-off
A Bietti, A Agarwal, J Langford
arXiv preprint arXiv:1802.04064, 2018
34*2018
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure
A Bietti, J Mairal
Advances in Neural Information Processing Systems (NIPS), 2017
332017
A Kernel Perspective for Regularizing Deep Neural Networks
A Bietti, G Mialon, D Chen, J Mairal
International Conference on Machine Learning (ICML), 2019
28*2019
Invariance and Stability of Deep Convolutional Representations
A Bietti, J Mairal
Advances in Neural Information Processing Systems (NIPS), 2017
212017
An online EM algorithm in hidden (semi-) Markov models for audio segmentation and clustering
A Bietti, F Bach, A Cont
IEEE International Conference on Acoustics, Speech and Signal Processing …, 2015
192015
Active learning for object detection on satellite images
A Bietti
Technical Report, Caltech, 2012
122012
Online learning for audio clustering and segmentation
A Bietti
ENS Cachan, 2014
52014
Counterfactual Learning of Continuous Stochastic Policies
H Zenati, A Bietti, M Martin, E Diemert, J Mairal
arXiv preprint arXiv:2004.11722, 2020
12020
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs
N Keriven, A Bietti, S Vaiter
Advances in Neural Information Processing Systems (NeurIPS), 2020
12020
Deep Equals Shallow for ReLU Networks in Kernel Regimes
A Bietti, F Bach
arXiv preprint arXiv:2009.14397, 2020
2020
Foundations of deep convolutional models through kernel methods
A Bietti
Université Grenoble Alpes, 2019
2019
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–13