Joan Bruna

Publication Activity (10 Years)

Years Active: 2010-2024
Publications (10 Years): 154

Top Venues

CoRR

NeurIPS

ICML

ICLR (Poster)

École Polytechnique, Palaiseau, France (PHD)

Education History

École Polytechnique, Palaiseau, France

PHD

Publications

Lei Chen, Joan Bruna, Alberto Bietti
How Truncating Weights Improves Reasoning in Language Models. CoRR (2024)
Noah Amsel, Gilad Yehudai, Joan Bruna
On the Benefits of Rank in Attention Layers. CoRR (2024)
Aaron Zweig, Joan Bruna
Symmetric Single Index Learning. ICLR (2024)
Joan Bruna, Benjamin Peherstorfer, Eric Vanden-Eijnden
Neural Galerkin schemes with active learning for high-dimensional evolution equations. J. Comput. Phys. 496 (2024)
Joan Bruna, Jiequn Han
Posterior Sampling with Denoising Oracles via Tilted Transport. CoRR (2024)
Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). COLT (2024)
Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna
Computational-Statistical Gaps in Gaussian Single-Index Models. CoRR (2024)
David Brandfonbrener, Ofir Nachum, Joan Bruna
Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation. NeurIPS (2023)
Alberto Bietti, Joan Bruna, Loucas Pillaud-Vivien
On Learning Gaussian Multi-index Models with Gradient Flow. CoRR (2023)
Vignesh Kothapalli, Tom Tirer, Joan Bruna
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks. CoRR (2023)
David Brandfonbrener, Ofir Nachum, Joan Bruna
Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation. CoRR (2023)
Carles Domingo-Enrich, Jiequn Han, Brandon Amos, Joan Bruna, Ricky T. Q. Chen
Stochastic Optimal Control Matching. CoRR (2023)
Joan Bruna, Loucas Pillaud-Vivien, Aaron Zweig
On Single Index Models beyond Gaussian Data. CoRR (2023)
Karl Otness, Laure Zanna, Joan Bruna
Data-driven multiscale modeling of subgrid parameterizations in climate models. CoRR (2023)
Florentin Guth, Etienne Lempereur, Joan Bruna, Stéphane Mallat
Conditionally Strongly Log-Concave Generative Models. CoRR (2023)
Florentin Guth, Etienne Lempereur, Joan Bruna, Stéphane Mallat
Conditionally Strongly Log-Concave Generative Models. ICML (2023)
Vignesh Kothapalli, Tom Tirer, Joan Bruna
A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks. NeurIPS (2023)
Aaron Zweig, Loucas Pillaud-Vivien, Joan Bruna
On Single-Index Models beyond Gaussian Data. NeurIPS (2023)
Aaron Zweig, Joan Bruna
Symmetric Single Index Learning. CoRR (2023)
Lei Chen, Joan Bruna
Beyond the Edge of Stability via Two-step Gradient Updates. ICML (2023)
Joan Bruna, Benjamin Peherstorfer, Eric Vanden-Eijnden
Neural Galerkin Scheme with Active Learning for High-Dimensional Evolution Equations. CoRR (2022)
Aaron Zweig, Joan Bruna
Towards Antisymmetric Neural Ansatz Separation. CoRR (2022)
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
On Feature Learning in Neural Networks with Global Convergence Guarantees. CoRR (2022)
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks. 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)
Carles Domingo-Enrich, Joan Bruna
Simultaneous Transport Evolution for Minimax Equilibria on Measures. CoRR (2022)
Aaron Zweig, Joan Bruna
Exponential Separations in Symmetric Neural Networks. 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)
Ilias Zadik, Min Jae Song, Alexander S. Wein, Joan Bruna
Lattice-Based Methods Surpass Sum-of-Squares in Clustering. COLT (2022)
Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna
Depth separation beyond radial functions. J. Mach. Learn. Res. 23 (2022)
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
Learning Single-Index Models with Shallow Neural Networks. CoRR (2022)
Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna
On feature learning in neural networks with global convergence guarantees. ICLR (2022)
Tom Tirer, Joan Bruna
Extended Unconstrained Features Model for Exploring Deep Neural Collapse. CoRR (2022)
Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song
Learning single-index models with shallow neural networks. NeurIPS (2022)
Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, Or Litany
Neural Fields as Learnable Kernels for 3D Reconstruction. CVPR (2022)
Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
Cartoon Explanations of Image Classifiers. ECCV (12) (2022)
Stefanos Zafeiriou, Michael M. Bronstein, Taco Cohen, Oriol Vinyals, Le Song, Jure Leskovec, Pietro Liò, Joan Bruna, Marco Gori
Guest Editorial: Non-Euclidean Machine Learning. IEEE Trans. Pattern Anal. Mach. Intell. 44 (2) (2022)
Tom Tirer, Joan Bruna
Extended Unconstrained Features Model for Exploring Deep Neural Collapse. ICML (2022)
Pau Batlle, Joan Bruna, Carlos Fernandez-Granda, Victor M. Preciado
Adaptive Test Allocation for Outbreak Detection and Tracking in Social Contact Networks. SIAM J. Control. Optim. 60 (2) (2022)
Lei Chen, Joan Bruna
On Gradient Descent Convergence beyond the Edge of Stability. CoRR (2022)
Grégoire Sergeant-Perthuis, Jakob Maier, Joan Bruna, Edouard Oyallon
On Non-Linear operators for Geometric Deep Learning. NeurIPS (2022)
Grégoire Sergeant-Perthuis, Jakob Maier, Joan Bruna, Edouard Oyallon
On Non-Linear operators for Geometric Deep Learning. CoRR (2022)
Aaron Zweig, Joan Bruna
Exponential Separations in Symmetric Neural Networks. NeurIPS (2022)
David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna
Quantile Filtered Imitation Learning. CoRR (2021)
Michael M. Bronstein, Joan Bruna, Taco Cohen, Petar Velickovic
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges. CoRR (2021)
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)
Tom Tirer, Joan Bruna, Raja Giryes
Kernel-Based Smoothness Analysis of Residual Networks. MSML (2021)
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
On Energy-Based Models with Overparametrized Shallow Neural Networks. ICML (2021)
Joan Bruna, Oded Regev, Min Jae Song, Yi Tang
Continuous LWE. STOC (2021)
Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
A Rate-Distortion Framework for Explaining Black-box Model Decisions. CoRR (2021)
David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna
Offline RL Without Off-Policy Evaluation. CoRR (2021)
Alberto Bietti, Luca Venturi, Joan Bruna
On the Sample Complexity of Learning under Geometric Stability. NeurIPS (2021)
David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna
Offline Contextual Bandits with Overparameterized Models. ICML (2021)
Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna
Depth separation beyond radial functions. CoRR (2021)
Karl Otness, Arvi Gjoka, Joan Bruna, Daniele Panozzo, Benjamin Peherstorfer, Teseo Schneider, Denis Zorin
An Extensible Benchmark Suite for Learning to Simulate Physical Systems. CoRR (2021)
Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg
A Permutation-Equivariant Neural Network Architecture For Auction Design. AAAI (2021)
Alberto Bietti, Luca Venturi, Joan Bruna
On the Sample Complexity of Learning with Geometric Stability. CoRR (2021)
Yossi Arjevani, Joan Bruna, Michael Field, Joe Kileel, Matthew Trager, Francis Williams
Symmetry Breaking in Symmetric Tensor Decomposition. CoRR (2021)
Karl Otness, Arvi Gjoka, Joan Bruna, Daniele Panozzo, Benjamin Peherstorfer, Teseo Schneider, Denis Zorin
An Extensible Benchmark Suite for Learning to Simulate Physical Systems. NeurIPS Datasets and Benchmarks (2021)
Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna
On Energy-Based Models with Overparametrized Shallow Neural Networks. CoRR (2021)
Lei Chen, Zhengdao Chen, Joan Bruna
On Graph Neural Networks versus Graph-Augmented MLPs. ICLR (2021)
Aaron Zweig, Joan Bruna
A Functional Perspective on Learning Symmetric Functions with Neural Networks. ICML (2021)
Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, Or Litany
Neural Fields as Learnable Kernels for 3D Reconstruction. CoRR (2021)
Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
Cartoon Explanations of Image Classifiers. CoRR (2021)
Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin
Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks. CVPR (2021)
David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna
Offline RL Without Off-Policy Evaluation. NeurIPS (2021)
Lei Chen, Zhengdao Chen, Joan Bruna
Learning the Relevant Substructures for Tasks on Graph Data. ICASSP (2021)
Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna, Kyunghyun Cho
Self-Supervised Equivariant Scene Synthesis from Video. CoRR (2021)
Min Jae Song, Ilias Zadik, Joan Bruna
On the Cryptographic Hardness of Learning Single Periodic Neurons. CoRR (2021)
Yihan He, Joan Bruna
Multi-fidelity Stability for Graph Representation Learning. CoRR (2021)
Ilias Zadik, Min Jae Song, Alexander S. Wein, Joan Bruna
Lattice-Based Methods Surpass Sum-of-Squares in Clustering. CoRR (2021)
Min Jae Song, Ilias Zadik, Joan Bruna
On the Cryptographic Hardness of Learning Single Periodic Neurons. NeurIPS (2021)
Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok
A Rate-Distortion Framework for Explaining Black-Box Model Decisions. xxAI@ICML (2020)
Zhengdao Chen, Grant M. Rotskoff, Joan Bruna, Eric Vanden-Eijnden
A Dynamical Central Limit Theorem for Shallow Neural Networks. NeurIPS (2020)
Lei Chen, Zhengdao Chen, Joan Bruna
On Graph Neural Networks versus Graph-Augmented MLPs. CoRR (2020)
Mathieu Andreux, Tomás Angles, Georgios Exarchakis, Roberto Leonarduzzi, Gaspar Rochette, Louis Thiry, John Zarka, Stéphane Mallat, Joakim Andén, Eugene Belilovsky, Joan Bruna, Vincent Lostanlen, Muawiz Chaudhary, Matthew J. Hirn, Edouard Oyallon, Sixin Zhang, Carmine-Emanuele Cella, Michael Eickenberg
Kymatio: Scattering Transforms in Python. J. Mach. Learn. Res. 21 (2020)
David Brandfonbrener, Joan Bruna
Geometric Insights into the Convergence of Nonlinear TD Learning. ICLR (2020)
David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna
Overfitting and Optimization in Offline Policy Learning. CoRR (2020)
Zhengdao Chen, Grant M. Rotskoff, Joan Bruna, Eric Vanden-Eijnden
A Dynamical Central Limit Theorem for Shallow Neural Networks. CoRR (2020)
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method. CoRR (2020)
Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg
A Permutation-Equivariant Neural Network Architecture For Auction Design. CoRR (2020)
Aaron Zweig, Joan Bruna
A Functional Perspective on Learning Symmetric Functions with Neural Networks. CoRR (2020)
Joan Bruna, Oded Regev, Min Jae Song, Yi Tang
Continuous LWE. CoRR (2020)
Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch, Grant M. Rotskoff, Joan Bruna
A mean-field analysis of two-player zero-sum games. CoRR (2020)
Cosmas Heiß, Ron Levie, Cinjon Resnick, Gitta Kutyniok, Joan Bruna
In-Distribution Interpretability for Challenging Modalities. CoRR (2020)
Donsub Rim, Luca Venturi, Joan Bruna, Benjamin Peherstorfer
Depth separation for reduced deep networks in nonlinear model reduction: Distilling shock waves in nonlinear hyperbolic problems. CoRR (2020)
Joan Bruna, Eldad Haber, Gitta Kutyniok, Thomas Pock, René Vidal
Special Issue on the Mathematical Foundations of Deep Learning in Imaging Science. J. Math. Imaging Vis. 62 (3) (2020)
Cinjon Resnick, Or Litany, Hugo Larochelle, Joan Bruna, Kyunghyun Cho
Learned Equivariant Rendering without Transformation Supervision. CoRR (2020)
Joan Bruna, Oded Regev, Min Jae Song, Yi Tang
Continuous LWE. Electron. Colloquium Comput. Complex. 27 (2020)
Fernando Gama, Alejandro Ribeiro, Joan Bruna
Stability of Graph Neural Networks to Relative Perturbations. ICASSP (2020)
Aaron Zweig, Joan Bruna
Provably Efficient Third-Person Imitation from Offline Observation. UAI (2020)
Aaron Zweig, Joan Bruna
Provably Efficient Third-Person Imitation from Offline Observation. CoRR (2020)
Fernando Gama, Joan Bruna, Alejandro Ribeiro
Stability Properties of Graph Neural Networks. IEEE Trans. Signal Process. 68 (2020)
Pau Batlle, Joan Bruna, Carlos Fernandez-Granda, Victor M. Preciado
Adaptive Test Allocation for Outbreak Detection and Tracking in Social Contact Networks. CoRR (2020)
Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch, Grant M. Rotskoff, Joan Bruna
A mean-field analysis of two-player zero-sum games. NeurIPS (2020)
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method. NeurIPS (2020)
Tom Tirer, Joan Bruna, Raja Giryes
Kernel-Based Smoothness Analysis of Residual Networks. CoRR (2020)
Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna
Extra-gradient with player sampling for faster convergence in n-player games. ICML (2020)
Matthew Trager, Kathlén Kohn, Joan Bruna
Pure and Spurious Critical Points: a Geometric Study of Linear Networks. ICLR (2020)
Zhengdao Chen, Lei Chen, Soledad Villar, Joan Bruna
Can graph neural networks count substructures? CoRR (2020)

Joan Bruna.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Joan Bruna