Alberto Bietti

According to our database, Alberto Bietti authored at least 42 papers between 2015 and 2024.

Collaborative distances:

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

2024

Understanding Factual Recall in Transformers via Associative Memories.

Eshaan Nichani, Jason D. Lee, Alberto Bietti

CoRR, 2024

How Truncating Weights Improves Reasoning in Language Models.

Lei Chen, Joan Bruna, Alberto Bietti

CoRR, 2024

Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task.

Siavash Golkar, Alberto Bietti, Mariel Pettee, Michael Eickenberg, Miles D. Cranmer, Keiya Hirashima, Géraud Krawezik, Nicholas Lourie, Michael McCabe, Rudy Morel, Ruben Ohana, Liam Holden Parker, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Shirley Ho

CoRR, 2024

Level Set Teleportation: An Optimization Perspective.

Aaron Mishkin, Alberto Bietti, Robert M. Gower

CoRR, 2024

Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models.

Frederik Kunstner, Robin Yadav, Alan Milligan, Mark Schmidt, Alberto Bietti

CoRR, 2024

Learning Associative Memories with Gradient Descent.

Vivien Cabannes, Berfin Simsek, Alberto Bietti

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

Scaling Laws for Associative Memories.

Vivien Cabannes, Elvis Dohmatob, Alberto Bietti

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

On Learning Gaussian Multi-index Models with Gradient Flow.

Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien

CoRR, 2023

AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models.

François Lanusse, Liam Holden Parker, Siavash Golkar, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Géraud Krawezik, Michael McCabe, Ruben Ohana, Mariel Pettee, Bruno Régaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

CoRR, 2023

Multiple Physics Pretraining for Physical Surrogate Models.

Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker, Ruben Ohana, Miles D. Cranmer, Alberto Bietti, Michael Eickenberg, Siavash Golkar, Géraud Krawezik, François Lanusse, Mariel Pettee, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

CoRR, 2023

xVal: A Continuous Number Encoding for Large Language Models.

Siavash Golkar, Mariel Pettee, Michael Eickenberg, Alberto Bietti, Miles D. Cranmer, Géraud Krawezik, François Lanusse, Michael McCabe, Ruben Ohana, Liam Holden Parker, Bruno Régaldo-Saint Blancard, Tiberiu Tesileanu, Kyunghyun Cho, Shirley Ho

CoRR, 2023

Birth of a Transformer: A Memory Viewpoint.

Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou

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

On Minimal Variations for Unsupervised Representation Learning.

Vivien Cabannes, Alberto Bietti, Randall Balestriero

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes.

Elvis Dohmatob, Alberto Bietti

CoRR, 2022

Efficient Kernel UCB for Contextual Bandits.

Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard

CoRR, 2022

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization.

Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu

CoRR, 2022

When does return-conditioned supervised learning work for offline reinforcement learning?

David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna

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

Learning single-index models with shallow neural networks.

Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song

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

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning.

Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu

Proceedings of the International Conference on Machine Learning, 2022

Approximation and Learning with Deep Convolutional Models: a Kernel Perspective.

Alberto Bietti

Proceedings of the Tenth International Conference on Learning Representations, 2022

Efficient Kernelized UCB for Contextual Bandits.

Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

A Contextual Bandit Bake-off.

Alberto Bietti, Alekh Agarwal, John Langford

J. Mach. Learn. Res., 2021

Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks.

Carles Domingo-Enrich, Alberto Bietti, Marylou Gabrié, Joan Bruna, Eric Vanden-Eijnden

CoRR, 2021

On the Sample Complexity of Learning with Geometric Stability.

Alberto Bietti, Luca Venturi, Joan Bruna

CoRR, 2021

On Approximation in Deep Convolutional Networks: a Kernel Perspective.

Alberto Bietti

CoRR, 2021

On the Universality of Graph Neural Networks on Large Random Graphs.

Nicolas Keriven, Alberto Bietti, Samuel Vaiter

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On the Sample Complexity of Learning under Geometric Stability.

Alberto Bietti, Luca Venturi, Joan Bruna

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

On Energy-Based Models with Overparametrized Shallow Neural Networks.

Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna

Proceedings of the 38th International Conference on Machine Learning, 2021

Deep Equals Shallow for ReLU Networks in Kernel Regimes.

Alberto Bietti, Francis R. Bach

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

2020

Optimization Approaches for Counterfactual Risk Minimization with Continuous Actions.

Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Julien Mairal

CoRR, 2020

Convergence and Stability of Graph Convolutional Networks on Large Random Graphs.

Nicolas Keriven, Alberto Bietti, Samuel Vaiter

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

2019

Foundations of deep convolutional models through kernel methods. (Méthodes à noyaux pour les réseaux convolutionnels profonds).

Alberto Bietti

PhD thesis, 2019

Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations.

Alberto Bietti, Julien Mairal

J. Mach. Learn. Res., 2019

On the Inductive Bias of Neural Tangent Kernels.

Alberto Bietti, Julien Mairal

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

A Kernel Perspective for Regularizing Deep Neural Networks.

Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

On Regularization and Robustness of Deep Neural Networks.

Alberto Bietti, Grégoire Mialon, Julien Mairal

CoRR, 2018

Practical Evaluation and Optimization of Contextual Bandit Algorithms.

Alberto Bietti, Alekh Agarwal, John Langford

CoRR, 2018

2017

Group Invariance and Stability to Deformations of Deep Convolutional Representations.

Alberto Bietti, Julien Mairal

CoRR, 2017

Invariance and Stability of Deep Convolutional Representations.

Alberto Bietti, Julien Mairal

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure.

Alberto Bietti, Julien Mairal

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2015

An online EM algorithm in hidden (semi-)Markov models for audio segmentation and clustering.

Alberto Bietti, Francis R. Bach, Arshia Cont

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015