Randall Balestriero

According to our database, Randall Balestriero authored at least 96 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors.

Vishwanath Saragadam, Randall Balestriero, Ashok Veeraraghavan, Richard G. Baraniuk

IEEE Trans. Pattern Anal. Mach. Intell., December, 2024

Cross-Entropy Is All You Need To Invert the Data Generating Process.

Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt

CoRR, 2024

The Fair Language Model Paradox.

Andrea Pinto, Tomer Galanti, Randall Balestriero

CoRR, 2024

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws.

Hai Huang, Randall Balestriero

CoRR, 2024

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods.

Daniel Otero, Rafael Mateus, Randall Balestriero

CoRR, 2024

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling.

Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim

CoRR, 2024

On the Geometry of Deep Learning.

Randall Balestriero, Ahmed Imtiaz Humayun, Richard G. Baraniuk

CoRR, 2024

𝕏-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs.

Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun

CoRR, 2024

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?

Mark Ibrahim, David A. Klindt, Randall Balestriero

CoRR, 2024

ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks.

Omer Ronen, Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk, Bin Yu

CoRR, 2024

Learning by Reconstruction Produces Uninformative Features For Perception.

Randall Balestriero, Yann LeCun

CoRR, 2024

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning.

Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano, Reihaneh Rabbany

CoRR, 2024

Deep Networks Always Grok and Here is Why.

Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk

Proceedings of the Forty-first International Conference on Machine Learning, 2024

How Learning by Reconstruction Produces Uninformative Features For Perception.

Randall Balestriero, Yann LeCun

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation.

Randall Balestriero, Romain Cosentino, Sarath Shekkizhar

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

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

Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent

Trans. Mach. Learn. Res., 2023

Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation.

Randall Balestriero, Romain Cosentino, Sarath Shekkizhar

CoRR, 2023

Training Dynamics of Deep Network Linear Regions.

Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk

CoRR, 2023

Martian time-series unraveled: A multi-scale nested approach with factorial variational autoencoders.

Ali Siahkoohi, Rudy Morel, Randall Balestriero, Erwan Allys, Grégory Sainton, Taichi Kawamura, Maarten V. de Hoop

CoRR, 2023

A Cookbook of Self-Supervised Learning.

Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Grégoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum

CoRR, 2023

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

Florian Bordes, Samuel Lavoie, Randall Balestriero, Nicolas Ballas, Pascal Vincent

CoRR, 2023

Towards Democratizing Joint-Embedding Self-Supervised Learning.

Florian Bordes, Randall Balestriero, Pascal Vincent

CoRR, 2023

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

Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner, Yann LeCun

CoRR, 2023

FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling.

Wei-Yin Ko, Daniel D'souza, Karina Nguyen, Randall Balestriero, Sara Hooker

CoRR, 2023

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

Randall Balestriero

CoRR, 2023

An Information Theory Perspective on Variance-Invariance-Covariance Regularization.

Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner, Yann LeCun

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Understanding the detrimental class-level effects of data augmentation.

Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Shanmukha Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank.

Quentin Garrido, Randall Balestriero, Laurent Najman, Yann LeCun

Proceedings of the International Conference on Machine Learning, 2023

The SSL Interplay: Augmentations, Inductive Bias, and Generalization.

Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti

Proceedings of the International Conference on Machine Learning, 2023

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

Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim

Proceedings of the Eleventh International Conference on Learning Representations, 2023

The hidden uniform cluster prior in self-supervised learning.

Mido Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

Vivien Cabannes, Léon Bottou, Yann LeCun, Randall Balestriero

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

On Minimal Variations for Unsupervised Representation Learning.

Vivien Cabannes, Alberto Bietti, Randall Balestriero

Proceedings of the IEEE International Conference on Acoustics, 2023

Police: Provably Optimal Linear Constraint Enforcement For Deep Neural Networks.

Randall Balestriero, Yann LeCun

Proceedings of the IEEE International Conference on Acoustics, 2023

Fast and Exact Enumeration of Deep Networks Partitions Regions.

Randall Balestriero, Yann LeCun

Proceedings of the IEEE International Conference on Acoustics, 2023

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

Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Max-Affine Spline Insights Into Deep Network Pruning.

Haoran You, Randall Balestriero, Zhihan Lu, Yutong Kou, Huihong Shi, Shunyao Zhang, Shang Wu, Yingyan Lin, Richard G. Baraniuk

Trans. Mach. Learn. Res., 2022

High Fidelity Visualization of What Your Self-Supervised Representation Knows About.

Florian Bordes, Randall Balestriero, Pascal Vincent

Trans. Mach. Learn. Res., 2022

Recurrent Scattering Network Detects Metastable Behavior in Polyphonic Seismo-Volcanic Signals for Volcano Eruption Forecasting.

Ángel Bueno Rodríguez, Randall Balestriero, Silvio De Angelis, M. Carmen Benítez, Luciano Zuccarello, Richard G. Baraniuk, Jesús M. Ibáñez, Maarten V. de Hoop

IEEE Trans. Geosci. Remote. Sens., 2022

The Hidden Uniform Cluster Prior in Self-Supervised Learning.

Mahmoud Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas

CoRR, 2022

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations.

Grégoire Mialon, Randall Balestriero, Yann LeCun

CoRR, 2022

Joint Embedding Self-Supervised Learning in the Kernel Regime.

Bobak Toussi Kiani, Randall Balestriero, Yubei Chen, Seth Lloyd, Yann LeCun

CoRR, 2022

Batch Normalization Explained.

Randall Balestriero, Richard G. Baraniuk

CoRR, 2022

What Do We Maximize in Self-Supervised Learning?

Ravid Shwartz-Ziv, Randall Balestriero, Yann LeCun

CoRR, 2022

Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head.

Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent

CoRR, 2022

Singular Value Perturbation and Deep Network Optimization.

Rudolf H. Riedi, Randall Balestriero, Richard G. Baraniuk

CoRR, 2022

NeuroView-RNN: It's About Time.

C. J. Barberan, Sina Alemohammad, Naiming Liu, Randall Balestriero, Richard G. Baraniuk

CoRR, 2022

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

Randall Balestriero, Ishan Misra, Yann LeCun

CoRR, 2022

projUNN: efficient method for training deep networks with unitary matrices.

Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Seth Lloyd

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training.

Randall Balestriero, Ishan Misra, Yann LeCun

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods.

Randall Balestriero, Yann LeCun

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The Effects of Regularization and Data Augmentation are Class Dependent.

Randall Balestriero, Léon Bottou, Yann LeCun

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk

Proceedings of the Tenth International Conference on Learning Representations, 2022

No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds.

Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis, Richard G. Baraniuk

Proceedings of the IEEE International Conference on Acoustics, 2022

DeepHull: Fast Convex Hull Approximation in High Dimensions.

Randall Balestriero, Zichao Wang, Richard G. Baraniuk

Proceedings of the IEEE International Conference on Acoustics, 2022

NeuroView-RNN: It's About Time.

C. J. Barberan, Sina Alemmohammad, Naiming Liu, Randall Balestriero, Richard G. Baraniuk

Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022

Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values.

Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Spatial Transformer K-Means.

Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang

Proceedings of the 56th Asilomar Conference on Signals, Systems, and Computers, ACSSC 2022, Pacific Grove, CA, USA, October 31, 2022

2021

Mad Max: Affine Spline Insights Into Deep Learning.

Randall Balestriero, Richard G. Baraniuk

Proc. IEEE, 2021

Learning in High Dimension Always Amounts to Extrapolation.

Randall Balestriero, Jerome Pesenti, Yann LeCun

CoRR, 2021

NeuroView: Explainable Deep Network Decision Making.

C. J. Barberan, Randall Balestriero, Richard G. Baraniuk

CoRR, 2021

Fast Jacobian-Vector Product for Deep Networks.

Randall Balestriero, Richard G. Baraniuk

CoRR, 2021

Max-Affine Spline Insights Into Deep Network Pruning.

Randall Balestriero, Haoran You, Zhihan Lu, Yutong Kou, Yingyan Lin, Richard G. Baraniuk

CoRR, 2021

Deep Autoencoders: From Understanding to Generalization Guarantees.

Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang

Proceedings of the Mathematical and Scientific Machine Learning, 2021

Interpretable and Learnable Super-Resolution Time-Frequency Representation.

Randall Balestriero, Hervé Glotin, Richard G. Baraniuk

Proceedings of the Mathematical and Scientific Machine Learning, 2021

The Recurrent Neural Tangent Kernel.

Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard G. Baraniuk

Proceedings of the 9th International Conference on Learning Representations, 2021

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

Sina Alemohammad, Hossein Babaei, Randall Balestriero, Matt Y. Cheung, Ahmed Imtiaz Humayun, Daniel LeJeune, Naiming Liu, Lorenzo Luzi, Jasper Tan, Zichao Wang, Richard G. Baraniuk

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Universal Frame Thresholding.

Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang

IEEE Signal Process. Lett., 2020

Interpretable Image Clustering via Diffeomorphism-Aware K-Means.

Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang

CoRR, 2020

Sparse Multi-Family Deep Scattering Network.

Romain Cosentino, Randall Balestriero

CoRR, 2020

Scalable Neural Tangent Kernel of Recurrent Architectures.

Sina Alemohammad, Randall Balestriero, Zichao Wang, Richard G. Baraniuk

CoRR, 2020

Provable Finite Data Generalization with Group Autoencoder.

Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang

CoRR, 2020

Ensembles of Generative Adversarial Networks for Disconnected Data.

Lorenzo Luzi, Randall Balestriero, Richard G. Baraniuk

CoRR, 2020

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

Randall Balestriero, Sébastien Paris, Richard G. Baraniuk

CoRR, 2020

Interpretable Super-Resolution via a Learned Time-Series Representation.

Randall Balestriero, Hervé Glotin, Richard G. Baraniuk

CoRR, 2020

SymJAX: symbolic CPU/GPU/TPU programming.

Randall Balestriero

CoRR, 2020

Max-Affine Spline Insights into Deep Generative Networks.

Randall Balestriero, Sébastien Paris, Richard G. Baraniuk

CoRR, 2020

Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks.

Randall Balestriero, Sébastien Paris, Richard G. Baraniuk

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

A Hessian Based Complexity Measure for Deep Networks.

Hamid Javadi, Randall Balestriero, Richard G. Baraniuk

CoRR, 2019

The Geometry of Deep Networks: Power Diagram Subdivision.

Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard G. Baraniuk

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Max-Affine Spline Perspective of Recurrent Neural Networks.

Zichao Wang, Randall Balestriero, Richard G. Baraniuk

Proceedings of the 7th International Conference on Learning Representations, 2019

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

Randall Balestriero, Richard G. Baraniuk

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

A Spline Theory of Deep Networks (Extended Version).

Randall Balestriero, Richard G. Baraniuk

CoRR, 2018

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

Randall Balestriero, Hervé Glotin, Richard G. Baraniuk

CoRR, 2018

Spline Filters For End-to-End Deep Learning.

Randall Balestriero, Romain Cosentino, Hervé Glotin, Richard G. Baraniuk

Proceedings of the 35th International Conference on Machine Learning, 2018

A Spline Theory of Deep Networks.

Randall Balestriero, Richard G. Baraniuk

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Overcomplete Frame Thresholding for Acoustic Scene Analysis.

Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Ankit B. Patel

CoRR, 2017

Semi-Supervised Learning via New Deep Network Inversion.

Randall Balestriero, Vincent Roger, Hervé Glotin, Richard G. Baraniuk

CoRR, 2017

Adaptive Partitioning Spline Neural Networks: Template Matching, Memorization, Inhibitor Connections, Inversion, Semi-Sup, Topology Search.

Randall Balestriero, Richard G. Baraniuk

CoRR, 2017

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

Randall Balestriero, Hervé Glotin

CoRR, 2017

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

Randall Balestriero

CoRR, 2017

Neural Decision Trees.

Randall Balestriero

CoRR, 2017

Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech.

Hervé Glotin, Julien Ricard, Randall Balestriero

Proceedings of the 5th International Conference on Learning Representations, 2017

2016

Fast Chirplet Transform feeding CNN, application to orca and bird bioacoustics.

Hervé Glotin, Julien Ricard, Randall Balestriero

CoRR, 2016

Best basis selection using sparsity driven multi-family wavelet transform.

Romain Cosentino, Randall Balestriero, Behnaam Aazhang

Proceedings of the 2016 IEEE Global Conference on Signal and Information Processing, 2016

2015

Scattering Decomposition for Massive Signal Classification: From Theory to Fast Algorithm and Implementation with Validation on International Bioacoustic Benchmark.

Randall Balestriero, Hervé Glotin

Proceedings of the IEEE International Conference on Data Mining Workshop, 2015