Randall Balestriero

Vivien A. Cabannes, Randall Balestriero, A. Bietti, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank

Yann LeCun, Laurent Najman, Randall Balestriero, 2022, arXiv.org.

Joint Embedding Self-Supervised Learning in the Kernel Regime

Yann LeCun, Randall Balestriero, Yubei Chen, 2022, ArXiv.

Singular Value Perturbation and Deep Network Optimization

Richard Baraniuk, Randall Balestriero, R. Riedi, 2022, Constructive Approximation.

Multiscale Residual Mixture of PCA: Dynamic Dictionaries for Optimal Basis Learning pdf

Randall Balestriero, Randall Balestriero, 2017, ArXiv.

Deep Neural Networks pdf

Richard G. Baraniuk, Randall Balestriero, D. Song, 2017 .

DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors

Richard Baraniuk, A. Veeraraghavan, Randall Balestriero, 2022, ArXiv.

Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels pdf

Zichao Wang, Richard G. Baraniuk, Ahmed Imtiaz Humayun, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Universal Frame Thresholding

Richard G. Baraniuk, Behnaam Aazhang, Randall Balestriero, 2020, IEEE Signal Processing Letters.

Max-Affine Spline Insights into Deep Generative Networks pdf

Richard Baraniuk, Randall Balestriero, Sebastien Paris, 2020, ArXiv.

Deep Autoencoders: From Understanding to Generalization Guarantees

Richard Baraniuk, Randall Balestriero, B. Aazhang, 2020, MSML.

Provable Finite Data Generalization with Group Autoencoder pdf

Behnaam Aazhang, Richard Baraniuk, Randall Balestriero, 2020, ArXiv.

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Vivien A. Cabannes, Yann LeCun, Randall Balestriero, 2023, ArXiv.

The Effects of Regularization and Data Augmentation are Class Dependent

L. Bottou, Yann LeCun, Randall Balestriero, 2022, NeurIPS.

Mad Max: Affine Spline Insights Into Deep Learning

Richard Baraniuk, Randall Balestriero, Richard Baraniuk, 2018, Proceedings of the IEEE.

MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining pdf

Ahmed Imtiaz Humayun, Richard Baraniuk, Randall Balestriero, 2021, ICLR.

TIVE NETWORK MANIFOLDS WITHOUT RETRAINING

Richard Baraniuk, Randall Balestriero, Deep Genera, 2022 .

A Cookbook of Self-Supervised Learning

Ari S. Morcos, Yann LeCun, H. Pirsiavash, 2023, ArXiv.

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Badr Youbi Idrissi, Pascal Vincent, Nicolas Ballas, 2022, ICLR.

A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments

Yann LeCun, Ishan Misra, Randall Balestriero, 2022, arXiv.org.

Ensembles of Generative Adversarial Networks for Disconnected Data pdf

Richard G. Baraniuk, Lorenzo Luzi, Randall Balestriero, 2020, ArXiv.

The Geometry of Deep Networks: Power Diagram Subdivision

Behnaam Aazhang, Richard Baraniuk, Randall Balestriero, 2019, NeurIPS.

From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference pdf

Richard G. Baraniuk, Randall Balestriero, Richard Baraniuk, 2018, ICLR.

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

Pascal Vincent, Nicolas Ballas, Randall Balestriero, 2023, ArXiv.

RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank

Yann LeCun, Laurent Najman, Randall Balestriero, 2022, ArXiv.

Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head

Randall Balestriero, 2023, ArXiv.

Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need

Vivien A. Cabannes, L. Bottou, Yann LeCun, 2023, ArXiv.

The Recurrent Neural Tangent Kernel pdf

Zichao Wang, Richard Baraniuk, Randall Balestriero, 2020, ICLR.

Anatomy of Continuous Mars SEIS and Pressure Data from Unsupervised Learning

Randall Balestriero, W. Banerdt, J. Clinton, 2021, Bulletin of the Seismological Society of America.

Clustering earthquake signals and background noises in continuous seismic data with unsupervised deep learning

Richard Baraniuk, Randall Balestriero, M. Campillo, 2020, Nature Communications.

Neural Decision Trees pdf

Randall Balestriero, Randall Balestriero, Randall Balestriero, 2017, ArXiv.

Learning in High Dimension Always Amounts to Extrapolation pdf

Yann LeCun, Randall Balestriero, Jerome Pesenti, 2021, ArXiv.

Deep learning for ethoacoustical mapping: Application to a single Cachalot long term recording on joint observatories in Vancouver Island

Randall Balestriero, H. Glotin, Scott Veirs, 2018, The Journal of the Acoustical Society of America.

NeuroView-RNN: It’s About Time

Richard Baraniuk, Randall Balestriero, Sina Alemohammad, 2022, FAccT.

Interpretable Image Clustering via Diffeomorphism-Aware K-Means pdf

Behnaam Aazhang, Yanis Bahroun, Anirvan M. Sengupta, 2020, ArXiv.

A Spline Theory of Deep Networks (Extended Version) pdf

Richard G. Baraniuk, Randall Balestriero, Richard Baraniuk, 2018, ArXiv.

Best basis selection using sparsity driven multi-family wavelet transform

Behnaam Aazhang, Randall Balestriero, Romain Cosentino, 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank

Yann LeCun, Laurent Najman, Randall Balestriero, 2022, ICML.

Towards Democratizing Joint-Embedding Self-Supervised Learning

Pascal Vincent, Randall Balestriero, Florian Bordes, 2023, arXiv.org.

A Cookbook of Self-Supervised Learning

Ari S. Morcos, Yann LeCun, H. Pirsiavash, 2023, ArXiv.

Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning

Pascal Vincent, Randall Balestriero, Florian Bordes, 2022, Trans. Mach. Learn. Res..

An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization

Tim G. J. Rudner, Yann LeCun, Kenji Kawaguchi, 2023, ArXiv.

Scalable Neural Tangent Kernel of Recurrent Architectures pdf

Zichao Wang, Richard Baraniuk, Randall Balestriero, 2020, ArXiv.

A Spline Theory of Deep Networks

Richard G. Baraniuk, Randall Balestriero, Richard Baraniuk, 2018, ICML.

The SSL Interplay: Augmentations, Inductive Bias, and Generalization

Vivien A. Cabannes, Yann LeCun, Randall Balestriero, 2023, ICML.

Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion pdf

Hervé Glotin, Richard G. Baraniuk, Randall Balestriero, 2018, ArXiv.

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

Ahmed Imtiaz Humayun, Richard Baraniuk, Randall Balestriero, 2023, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling

Sara Hooker, Randall Balestriero, Wei-Yin Ko, 2023, ArXiv.

Max-Affine Spline Insights Into Deep Network Pruning

Richard Baraniuk, Randall Balestriero, Haoran You, 2021, Trans. Mach. Learn. Res..

Fast Jacobian-Vector Product for Deep Networks pdf

Richard Baraniuk, Randall Balestriero, Richard Baraniuk, 2021, ArXiv.

UNDERSTANDING THE CLASS-SPECIFIC EFFECTS OF DATA AUGMENTATIONS

Ramakrishna Vedantam, Randall Balestriero, P. Kirichenko, 2023 .

Spatial Transformer K-Means

Anirvan M. Sengupta, Richard Baraniuk, Randall Balestriero, 2022, 2022 56th Asilomar Conference on Signals, Systems, and Computers.

182 Deep Neural Networks

Richard Baraniuk, Randall Balestriero, 2022 .

Linear Time Complexity Deep Fourier Scattering Network and Extension to Nonlinear Invariants pdf

Hervé Glotin, Randall Balestriero, Randall Balestriero, 2017, ArXiv.

DeepHull: Fast Convex Hull Approximation in High Dimensions

Richard Baraniuk, Randall Balestriero, Zichao Wang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Analytical Probability Distributions and EM-Learning for Deep Generative Networks pdf

Richard G. Baraniuk, Randall Balestriero, Sebastien Paris, 2020, ArXiv.

Wavelet Learning by Adaptive Hermite Cubic Splines applied to Bioacoustic Chirps

Hervé Glotin, Randall Balestriero, Randall Balestriero, 2019, OCEANS 2019 - Marseille.

Spline Filters For End-to-End Deep Learning

Hervé Glotin, Richard G. Baraniuk, Randall Balestriero, 2018, ICML.

Police: Provably Optimal Linear Constraint Enforcement For Deep Neural Networks

Yann LeCun, Randall Balestriero, 2022, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need

Vivien A. Cabannes, L. Bottou, Yann LeCun, 2023, ArXiv.

Deep Neural Networks

Richard Baraniuk, Randall Balestriero, 2023 .