Randall Balestriero
Randall Balestriero
Facebook AI Research New York
Verified email at fb.com - Homepage
Cited by
Cited by
A spline theory of deep learning
R Balestriero, R Baraniuk
International Conference on Machine Learning, 374-383, 2018
Mad max: Affine spline insights into deep learning
R Balestriero, RG Baraniuk
Proceedings of the IEEE, 1-24, 2020
Neural decision trees
R Balestriero
arXiv preprint arXiv:1702.07360, 2017
Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning
L Seydoux, R Balestriero, P Poli, M De Hoop, M Campillo, R Baraniuk
Nature communications 11 (1), 1-12, 2020
The recurrent neural tangent kernel
S Alemohammad, Z Wang, R Balestriero, R Baraniuk
International Conference on Learning Representations, 2020
Spline filters for end-to-end deep learning
R Balestriero, R Cosentino, H Glotin, R Baraniuk
International conference on machine learning, 364-373, 2018
Fast chirplet transform injects priors in deep learning of animal calls and speech
H Glotin, J Ricard, R Balestriero
International Conference on Learning Representations Workshop, 2017
The geometry of deep networks: Power diagram subdivision
R Balestriero, R Cosentino, B Aazhang, R Baraniuk
Advances in Neural Information Processing Systems 32, 15832--15841, 2019
Implicit rugosity regularization via data augmentation
D LeJeune, R Balestriero, H Javadi, RG Baraniuk
arXiv preprint arXiv:1905.11639, 2019
Scattering decomposition for massive signal classification: from theory to fast algorithm and implementation with validation on international bioacoustic benchmark
R Balestriero, H Glotin
2015 IEEE International Conference on Data Mining Workshop (ICDMW), 753-761, 2015
A max-affine spline perspective of recurrent neural networks
Z Wang, R Balestriero, R Baraniuk
International Conference on Learning Representations, 2018
Semi-supervised learning enabled by multiscale deep neural network inversion
R Balestriero, H Glotin, R Baraniuk
arXiv preprint arXiv:1802.10172, 2018
Enhanced feature extraction using the Morlet transform on 1 MHz recordings reveals the complex nature of Amazon River dolphin (Inia geoffrensis) clicks
M Trone, H Glotin, R Balestriero, DE Bonnett
The Journal of the Acoustical Society of America 138 (3), 1904-1904, 2015
From hard to soft: Understanding deep network nonlinearities via vector quantization and statistical inference
R Balestriero, RG Baraniuk
International Conference on Learning Representations, 2018
Best basis selection using sparsity driven multi-family wavelet transform
R Cosentino, R Balestriero, B Aazhang
2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2016
Linear time complexity deep Fourier scattering network and extension to nonlinear invariants
R Balestriero, H Glotin
arXiv preprint arXiv:1707.05841, 2017
Universal Frame Thresholding
R Cosentino, R Balestriero, RG Baraniuk, B Aazhang
IEEE Signal Processing Letters 27, 1115-1119, 2020
Max-affine spline insights into deep generative networks
R Balestriero, S Paris, R Baraniuk
arXiv preprint arXiv:2002.11912, 2020
All clicks are not created equally: Variations in high-frequency acoustic signal parameters of the Amazon river dolphin (Inia geoffrensis)
M Trone, R Balestriero, H Glotin, BE David
The Journal of the Acoustical Society of America 136 (4), 2217-2217, 2014
Learning in high dimension always amounts to extrapolation
R Balestriero, J Pesenti, Y LeCun
arXiv preprint arXiv:2110.09485, 2021
The system can't perform the operation now. Try again later.
Articles 1–20