Alberto Bietti

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 51

Top Topics

Optimization Approaches

Continuous Action

Top Venues

Publications

Lei Chen, Joan Bruna, Alberto Bietti
How Truncating Weights Improves Reasoning in Language Models. CoRR (2024)
Frederik Kunstner, Robin Yadav, Alan Milligan, Mark Schmidt, Alberto Bietti
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models. CoRR (2024)
Vivien Cabannes, Elvis Dohmatob, Alberto Bietti
Scaling Laws for Associative Memories. ICLR (2024)
Aaron Mishkin, Alberto Bietti, Robert M. Gower
Level Set Teleportation: An Optimization Perspective. CoRR (2024)
Vivien Cabannes, Berfin Simsek, Alberto Bietti
Learning Associative Memories with Gradient Descent. CoRR (2024)
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
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task. CoRR (2024)
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
Multiple Physics Pretraining for Physical Surrogate Models. CoRR (2023)
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
xVal: A Continuous Number Encoding for Large Language Models. CoRR (2023)
Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
The SSL Interplay: Augmentations, Inductive Bias, and Generalization. CoRR (2023)
Vivien Cabannes, Alberto Bietti, Randall Balestriero
On Minimal Variations for Unsupervised Representation Learning. ICASSP (2023)
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
Birth of a Transformer: A Memory Viewpoint. NeurIPS (2023)
Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien
On Learning Gaussian Multi-index Models with Gradient Flow. CoRR (2023)
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
AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models. CoRR (2023)
Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
Birth of a Transformer: A Memory Viewpoint. CoRR (2023)
Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
The SSL Interplay: Augmentations, Inductive Bias, and Generalization. ICML (2023)
Vivien Cabannes, Elvis Dohmatob, Alberto Bietti
Scaling Laws for Associative Memories. CoRR (2023)
Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard
Efficient Kernel UCB for Contextual Bandits. CoRR (2022)
David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
When does return-conditioned supervised learning work for offline reinforcement learning? CoRR (2022)
David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
When does return-conditioned supervised learning work for offline reinforcement learning? NeurIPS (2022)
Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard
Efficient Kernelized UCB for Contextual Bandits. AISTATS (2022)
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
Learning Single-Index Models with Shallow Neural Networks. CoRR (2022)
Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning. ICML (2022)
Vivien Cabannes, Alberto Bietti, Randall Balestriero
On minimal variations for unsupervised representation learning. CoRR (2022)
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
Learning single-index models with shallow neural networks. NeurIPS (2022)
Alberto Bietti
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective. ICLR (2022)
Elvis Dohmatob, Alberto Bietti
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes. CoRR (2022)
Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization. CoRR (2022)
Carles Domingo-Enrich, Alberto Bietti, Marylou Gabrié, Joan Bruna, Eric Vanden-Eijnden
Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks. CoRR (2021)
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
On Energy-Based Models with Overparametrized Shallow Neural Networks. ICML (2021)
Alberto Bietti, Luca Venturi, Joan Bruna
On the Sample Complexity of Learning under Geometric Stability. NeurIPS (2021)
Alberto Bietti, Luca Venturi, Joan Bruna
On the Sample Complexity of Learning with Geometric Stability. CoRR (2021)
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
On Energy-Based Models with Overparametrized Shallow Neural Networks. CoRR (2021)
Nicolas Keriven, Alberto Bietti, Samuel Vaiter
On the Universality of Graph Neural Networks on Large Random Graphs. NeurIPS (2021)
Nicolas Keriven, Alberto Bietti, Samuel Vaiter
On the Universality of Graph Neural Networks on Large Random Graphs. CoRR (2021)
Alberto Bietti
On Approximation in Deep Convolutional Networks: a Kernel Perspective. CoRR (2021)
Alberto Bietti, Francis R. Bach
Deep Equals Shallow for ReLU Networks in Kernel Regimes. ICLR (2021)
Alberto Bietti, Alekh Agarwal, John Langford
A Contextual Bandit Bake-off. J. Mach. Learn. Res. 22 (2021)
Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Julien Mairal
Optimization Approaches for Counterfactual Risk Minimization with Continuous Actions. CoRR (2020)
Nicolas Keriven, Alberto Bietti, Samuel Vaiter
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs. NeurIPS (2020)
Nicolas Keriven, Alberto Bietti, Samuel Vaiter
Convergence and Stability of Graph Convolutional Networks on Large Random Graphs. CoRR (2020)
Alberto Bietti, Francis R. Bach
Deep Equals Shallow for ReLU Networks in Kernel Regimes. CoRR (2020)
Alberto Bietti, Julien Mairal
Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations. J. Mach. Learn. Res. 20 (2019)
Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal
A Kernel Perspective for Regularizing Deep Neural Networks. ICML (2019)
Alberto Bietti, Julien Mairal
On the Inductive Bias of Neural Tangent Kernels. NeurIPS (2019)
Alberto Bietti, Julien Mairal
On the Inductive Bias of Neural Tangent Kernels. CoRR (2019)
Alberto Bietti, Grégoire Mialon, Julien Mairal
On Regularization and Robustness of Deep Neural Networks. CoRR (2018)
Alberto Bietti, Alekh Agarwal, John Langford
Practical Evaluation and Optimization of Contextual Bandit Algorithms. CoRR (2018)
Alberto Bietti, Julien Mairal
Invariance and Stability of Deep Convolutional Representations. NIPS (2017)
Alberto Bietti, Julien Mairal
Group Invariance and Stability to Deformations of Deep Convolutional Representations. CoRR (2017)
Alberto Bietti, Julien Mairal
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure. NIPS (2017)
Alberto Bietti, Julien Mairal
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure. CoRR (2016)
Alberto Bietti, Francis R. Bach, Arshia Cont
An online EM algorithm in hidden (semi-)Markov models for audio segmentation and clustering. ICASSP (2015)