Alberto Bietti

81 papers A* 22A 2Misc 2Journal 52Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Learning to Recall with Transformers Beyond Orthogonal Embeddings. CoRR Nuri Mert Vural, Alberto Bietti, Mahdi Soltanolkotabi, Denny Wu
2026	J	`jnl`	Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents. CoRR Jacopo Teneggi, S. M. Bargeen A. Turzo, Tanya Marwah, Alberto Bietti, P. Douglas Renfrew, Vikram Khipple Mulligan, Siavash Golkar
2026	J	`jnl`	Representation Learning for Spatiotemporal Physical Systems. CoRR Helen Qu, Rudy Morel, Michael McCabe, Alberto Bietti, François Lanusse, Shirley Ho, Yann LeCun
2026	J	`jnl`	Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory. CoRR Juno Kim, Eshaan Nichani, Denny Wu, Alberto Bietti, Jason D. Lee
2026	J	`jnl`	Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge. CoRR Bhavya Vasudeva, Puneesh Deora, Alberto Bietti, Vatsal Sharan, Christos Thrampoulidis
2025	J	`jnl`	Aristotle: IMO-level Automated Theorem Proving. CoRR Tudor Achim, Alex Best, Alberto Bietti, Kevin Der, Mathïs Fédérico, Sergei Gukov, Daniel Halpern-Leistner, Kirsten Henningsgard, Yury Kudryashov, Alexander Meiburg, Martin Michelsen, Riley Patterson, Eric Rodriguez, Laura Scharff, Vikram Shanker, Vladmir Sicca, Hari Sowrirajan, Aidan Swope, Matyas Tamas, Vlad Tenev, Jonathan Thomm, Harold Williams, Lawrence Wu
2025	A*	`conf`	BAnG: Bidirectional Anchored Generation for Conditional RNA Design. ICML Roman Klypa, Alberto Bietti, Sergei Grudinin
2025	J	`jnl`	BAnG: Bidirectional Anchored Generation for Conditional RNA Design. CoRR Roman Klypa, Alberto Bietti, Sergei Grudinin
2025	J	`jnl`	Counterfactual Learning of Stochastic Policies with Continuous Actions. Trans. Mach. Learn. Res. Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Pierre Gaillard, Julien Mairal
2025	A*	`conf`	Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers. ICLR Lei Chen, Joan Bruna, Alberto Bietti
2025	J	`jnl`	Emergence of Linear Truth Encodings in Language Models. CoRR Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti
2025	J	`jnl`	From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers. CoRR Ryotaro Kawata, Yujin Song, Alberto Bietti, Naoki Nishikawa, Taiji Suzuki, Samuel Vaiter, Denny Wu
2025	J	`jnl`	GSM-Agent: Understanding Agentic Reasoning Using Controllable Environments. CoRR Hanlin Zhu, Tianyu Guo, Song Mei, Stuart Russell, Nikhil Ghosh, Alberto Bietti, Jiantao Jiao
2025	A*	`conf`	In-Context Denoising with One-Layer Transformers: Connections between Attention and Associative Memory Retrieval. ICML Matthew Smart, Alberto Bietti, Anirvan M. Sengupta
2025	J	`jnl`	In-context denoising with one-layer transformers: connections between attention and associative memory retrieval. CoRR Matthew Smart, Alberto Bietti, Anirvan M. Sengupta
2025	A*	`conf`	Learning Compositional Functions with Transformers from Easy-to-Hard Data. COLT Zixuan Wang, Eshaan Nichani, Alberto Bietti, Alex Damian, Daniel Hsu, Jason D. Lee, Denny Wu
2025	J	`jnl`	Learning Compositional Functions with Transformers from Easy-to-Hard Data. CoRR Zixuan Wang, Eshaan Nichani, Alberto Bietti, Alex Damian, Daniel Hsu, Jason D. Lee, Denny Wu
2025	A	`conf`	Level Set Teleportation: An Optimization Perspective. AISTATS Aaron Mishkin, Alberto Bietti, Robert M. Gower
2025	J	`jnl`	Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model. CoRR Rio Alexa Fear, Payel Mukhopadhyay, Michael McCabe, Alberto Bietti, Miles D. Cranmer
2025	J	`jnl`	Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme. CoRR Rudy Morel, Francesco Pio Ramunno, Jeff Shen, Alberto Bietti, Kyunghyun Cho, Miles D. Cranmer, Siavash Golkar, Olexandr Gugnin, Géraud Krawezik, Tanya Marwah, Michael McCabe, Lucas Meyer, Payel Mukhopadhyay, Ruben Ohana, Liam Holden Parker, Helen Qu, François Rozet, K. D. Leka, François Lanusse, David Fouhey, Shirley Ho
2025	A*	`conf`	Understanding Factual Recall in Transformers via Associative Memories. ICLR Eshaan Nichani, Jason D. Lee, Alberto Bietti
2025	J	`jnl`	Understanding the Mechanisms of Fast Hyperparameter Transfer. CoRR Nikhil Ghosh, Denny Wu, Alberto Bietti
2025	J	`jnl`	Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning. CoRR Jeff Shen, François Lanusse, Liam Holden Parker, Ollie Liu, Tom Hehir, Leopoldo Sarra, Lucas Meyer, Micah Bowles, Sebastian Wagner-Carena, Helen Qu, Siavash Golkar, Alberto Bietti, Hatim Bourfoune, Nathan Cassereau, Pierre Cornette, Keiya Hirashima, Géraud Krawezik, Ruben Ohana, Nicholas Lourie, Michael McCabe, Rudy Morel, Payel Mukhopadhyay, Mariel Pettee, Bruno Régaldo-Saint Blancard, Kyunghyun Cho, Miles D. Cranmer, Shirley Ho
2025	J	`jnl`	Walrus: A Cross-Domain Foundation Model for Continuum Dynamics. CoRR Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Régaldo-Saint Blancard, François Rozet, Cristiana Diaconu, Lucas Meyer, Kaze W. K. Wong, Hadi Sotoudeh, Alberto Bietti, Irina Espejo, Rio Fear, Siavash Golkar, Tom Hehir, Keiya Hirashima, Géraud Krawezik, François Lanusse, Rudy Morel, Ruben Ohana, Liam Holden Parker, Mariel Pettee, Jeff Shen, Kyunghyun Cho, Miles D. Cranmer, Shirley Ho
2024	J	`jnl`	Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task. CoRR 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
2024	A*	`conf`	Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models. NeurIPS Frederik Kunstner, Alan Milligan, Robin Yadav, Mark Schmidt, Alberto Bietti
2024	J	`jnl`	Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models. CoRR Frederik Kunstner, Robin Yadav, Alan Milligan, Mark Schmidt, Alberto Bietti
2024	J	`jnl`	How Truncating Weights Improves Reasoning in Language Models. CoRR Lei Chen, Joan Bruna, Alberto Bietti
2024	A*	`conf`	Learning Associative Memories with Gradient Descent. ICML Vivien Cabannes, Berfin Simsek, Alberto Bietti
2024	J	`jnl`	Learning Associative Memories with Gradient Descent. CoRR Vivien Cabannes, Berfin Simsek, Alberto Bietti
2024	J	`jnl`	Level Set Teleportation: An Optimization Perspective. CoRR Aaron Mishkin, Alberto Bietti, Robert M. Gower
2024	A*	`conf`	Multiple Physics Pretraining for Spatiotemporal Surrogate Models. NeurIPS 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
2024	A*	`conf`	Scaling Laws for Associative Memories. ICLR Vivien Cabannes, Elvis Dohmatob, Alberto Bietti
2024	J	`jnl`	Understanding Factual Recall in Transformers via Associative Memories. CoRR Eshaan Nichani, Jason D. Lee, Alberto Bietti
2023	J	`jnl`	AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models. CoRR 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
2023	A*	`conf`	Birth of a Transformer: A Memory Viewpoint. NeurIPS Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
2023	J	`jnl`	Birth of a Transformer: A Memory Viewpoint. CoRR Alberto Bietti, Vivien Cabannes, Diane Bouchacourt, Hervé Jégou, Léon Bottou
2023	J	`jnl`	Multiple Physics Pretraining for Physical Surrogate Models. CoRR 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
2023	J	`jnl`	On Learning Gaussian Multi-index Models with Gradient Flow. CoRR Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien
2023	Misc	`conf`	On Minimal Variations for Unsupervised Representation Learning. ICASSP Vivien Cabannes, Alberto Bietti, Randall Balestriero
2023	J	`jnl`	Scaling Laws for Associative Memories. CoRR Vivien Cabannes, Elvis Dohmatob, Alberto Bietti
2023	A*	`conf`	The SSL Interplay: Augmentations, Inductive Bias, and Generalization. ICML Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
2023	J	`jnl`	The SSL Interplay: Augmentations, Inductive Bias, and Generalization. CoRR Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
2023	J	`jnl`	xVal: A Continuous Number Encoding for Large Language Models. CoRR 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
2022	A*	`conf`	Approximation and Learning with Deep Convolutional Models: a Kernel Perspective. ICLR Alberto Bietti
2022	J	`jnl`	Efficient Kernel UCB for Contextual Bandits. CoRR Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard
2022	A	`conf`	Efficient Kernelized UCB for Contextual Bandits. AISTATS Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal, Matthieu Martin, Pierre Gaillard
2022	J	`jnl`	Learning Single-Index Models with Shallow Neural Networks. CoRR Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
2022	A*	`conf`	Learning single-index models with shallow neural networks. NeurIPS Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
2022	J	`jnl`	On minimal variations for unsupervised representation learning. CoRR Vivien Cabannes, Alberto Bietti, Randall Balestriero
2022	J	`jnl`	On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes. CoRR Elvis Dohmatob, Alberto Bietti
2022	A*	`conf`	Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning. ICML Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
2022	J	`jnl`	Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization. CoRR Alberto Bietti, Chen-Yu Wei, Miroslav Dudík, John Langford, Zhiwei Steven Wu
2022	A*	`conf`	When does return-conditioned supervised learning work for offline reinforcement learning? NeurIPS David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
2022	J	`jnl`	When does return-conditioned supervised learning work for offline reinforcement learning? CoRR David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna
2021	J	`jnl`	A Contextual Bandit Bake-off. J. Mach. Learn. Res. Alberto Bietti, Alekh Agarwal, John Langford
2021	A*	`conf`	Deep Equals Shallow for ReLU Networks in Kernel Regimes. ICLR Alberto Bietti, Francis R. Bach
2021	J	`jnl`	Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks. CoRR Carles Domingo-Enrich, Alberto Bietti, Marylou Gabrié, Joan Bruna, Eric Vanden-Eijnden
2021	J	`jnl`	On Approximation in Deep Convolutional Networks: a Kernel Perspective. CoRR Alberto Bietti
2021	A*	`conf`	On Energy-Based Models with Overparametrized Shallow Neural Networks. ICML Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
2021	J	`jnl`	On Energy-Based Models with Overparametrized Shallow Neural Networks. CoRR Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
2021	A*	`conf`	On the Sample Complexity of Learning under Geometric Stability. NeurIPS Alberto Bietti, Luca Venturi, Joan Bruna
2021	J	`jnl`	On the Sample Complexity of Learning with Geometric Stability. CoRR Alberto Bietti, Luca Venturi, Joan Bruna
2021	A*	`conf`	On the Universality of Graph Neural Networks on Large Random Graphs. NeurIPS Nicolas Keriven, Alberto Bietti, Samuel Vaiter
2021	J	`jnl`	On the Universality of Graph Neural Networks on Large Random Graphs. CoRR Nicolas Keriven, Alberto Bietti, Samuel Vaiter
2020	A*	`conf`	Convergence and Stability of Graph Convolutional Networks on Large Random Graphs. NeurIPS Nicolas Keriven, Alberto Bietti, Samuel Vaiter
2020	J	`jnl`	Convergence and Stability of Graph Convolutional Networks on Large Random Graphs. CoRR Nicolas Keriven, Alberto Bietti, Samuel Vaiter
2020	J	`jnl`	Deep Equals Shallow for ReLU Networks in Kernel Regimes. CoRR Alberto Bietti, Francis R. Bach
2020	J	`jnl`	Optimization Approaches for Counterfactual Risk Minimization with Continuous Actions. CoRR Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Julien Mairal
2019	A*	`conf`	A Kernel Perspective for Regularizing Deep Neural Networks. ICML Alberto Bietti, Grégoire Mialon, Dexiong Chen, Julien Mairal
2019	—	`—`	Foundations of deep convolutional models through kernel methods. (Méthodes à noyaux pour les réseaux convolutionnels profonds). Alberto Bietti
2019	J	`jnl`	Group Invariance, Stability to Deformations, and Complexity of Deep Convolutional Representations. J. Mach. Learn. Res. Alberto Bietti, Julien Mairal
2019	A*	`conf`	On the Inductive Bias of Neural Tangent Kernels. NeurIPS Alberto Bietti, Julien Mairal
2019	J	`jnl`	On the Inductive Bias of Neural Tangent Kernels. CoRR Alberto Bietti, Julien Mairal
2018	J	`jnl`	On Regularization and Robustness of Deep Neural Networks. CoRR Alberto Bietti, Grégoire Mialon, Julien Mairal
2018	J	`jnl`	Practical Evaluation and Optimization of Contextual Bandit Algorithms. CoRR Alberto Bietti, Alekh Agarwal, John Langford
2017	J	`jnl`	Group Invariance and Stability to Deformations of Deep Convolutional Representations. CoRR Alberto Bietti, Julien Mairal
2017	—	`conf`	Invariance and Stability of Deep Convolutional Representations. NIPS Alberto Bietti, Julien Mairal
2017	—	`conf`	Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure. NIPS Alberto Bietti, Julien Mairal
2016	J	`jnl`	Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure. CoRR Alberto Bietti, Julien Mairal
2015	Misc	`conf`	An online EM algorithm in hidden (semi-)Markov models for audio segmentation and clustering. ICASSP Alberto Bietti, Francis R. Bach, Arshia Cont