Bruna, Joan

70 publications

NeurIPS 2025 Axial Neural Networks for Dimension-Free Foundation Models Hyunsu Kim, Jonggeon Park, Joan Bruna, Hongseok Yang, Juho Lee

NeurIPS 2025 Compositional Reasoning with Transformers, RNNs, and Chain of Thought Gilad Yehudai, Noah Amsel, Joan Bruna

ICLR 2025 Distributional Associations vs In-Context Reasoning: A Study of Feed-Forward and Attention Layers Lei Chen, Joan Bruna, Alberto Bietti

NeurIPS 2025 Emergence of Linear Truth Encodings in Language Models Shauli Ravfogel, Gilad Yehudai, Tal Linzen, Joan Bruna, Alberto Bietti

COLT 2025 Mean-Field Analysis of Polynomial-Width Two-Layer Neural Network Beyond Finite Time Horizon Margalit Glasgow, Denny Wu, Joan Bruna

ICLR 2025 Quality over Quantity in Attention Layers: When Adding More Heads Hurts Noah Amsel, Gilad Yehudai, Joan Bruna

NeurIPS 2025 The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models Alex Damian, Jason D. Lee, Joan Bruna

ICML 2025 Thermalizer: Stable Autoregressive Neural Emulation of Spatiotemporal Chaos Christian Pedersen, Laure Zanna, Joan Bruna

COLT 2024 Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract) Alex Damian, Loucas Pillaud-Vivien, Jason Lee, Joan Bruna

ICMLW 2024 How Truncating Weights Improves Reasoning in Language Models Lei Chen, Joan Bruna, Alberto Bietti

ICMLW 2024 How Truncating Weights Improves Reasoning in Language Models Lei Chen, Joan Bruna, Alberto Bietti

NeurIPS 2024 Provable Posterior Sampling with Denoising Oracles via Tilted Transport Joan Bruna, Jiequn Han

NeurIPS 2024 Stochastic Optimal Control Matching Carles Domingo-Enrich, Jiequn Han, Brandon Amos, Joan Bruna, Ricky T. Q. Chen

ICLR 2024 Symmetric Single Index Learning Aaron Zweig, Joan Bruna

NeurIPS 2023 A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks Vignesh Kothapalli, Tom Tirer, Joan Bruna

ICML 2023 Beyond the Edge of Stability via Two-Step Gradient Updates Lei Chen, Joan Bruna

ICML 2023 Conditionally Strongly Log-Concave Generative Models Florentin Guth, Etienne Lempereur, Joan Bruna, Stéphane Mallat

NeurIPS 2023 Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation David Brandfonbrener, Ofir Nachum, Joan Bruna

NeurIPS 2023 On Single-Index Models Beyond Gaussian Data Aaron Zweig, Loucas Pillaud-Vivien, Joan Bruna

ICMLW 2023 Reliable Coarse-Grained Turbulent Simulations Through Combined Offline Learning and Neural Emulation Christian Pedersen, Laure Zanna, Joan Bruna, Pavel Perezhogin

ECCV 2022 Cartoon Explanations of Image Classifiers Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok

JMLR 2022 Depth Separation Beyond Radial Functions Luca Venturi, Samy Jelassi, Tristan Ozuch, Joan Bruna

NeurIPS 2022 Exponential Separations in Symmetric Neural Networks Aaron Zweig, Joan Bruna

ICML 2022 Extended Unconstrained Features Model for Exploring Deep Neural Collapse Tom Tirer, Joan Bruna

COLT 2022 Lattice-Based Methods Surpass Sum-of-Squares in Clustering Ilias Zadik, Min Jae Song, Alexander S Wein, Joan Bruna

NeurIPS 2022 Learning Single-Index Models with Shallow Neural Networks Alberto Bietti, Joan Bruna, Clayton Sanford, Min Jae Song

CVPR 2022 Neural Fields as Learnable Kernels for 3D Reconstruction Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, Or Litany

ICLR 2022 On Feature Learning in Neural Networks with Global Convergence Guarantees Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna

NeurIPS 2022 On Non-Linear Operators for Geometric Deep Learning Grégoire Sergeant-Perthuis, Jakob Maier, Joan Bruna, Edouard Oyallon

NeurIPS 2022 When Does Return-Conditioned Supervised Learning Work for Offline Reinforcement Learning? David Brandfonbrener, Alberto Bietti, Jacob Buckman, Romain Laroche, Joan Bruna

ICML 2021 A Functional Perspective on Learning Symmetric Functions with Neural Networks Aaron Zweig, Joan Bruna

AAAI 2021 A Permutation-Equivariant Neural Network Architecture for Auction Design Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg

CVPR 2021 Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin

ICML 2021 Offline Contextual Bandits with Overparameterized Models David Brandfonbrener, William Whitney, Rajesh Ranganath, Joan Bruna

NeurIPS 2021 Offline RL Without Off-Policy Evaluation David Brandfonbrener, Will Whitney, Rajesh Ranganath, Joan Bruna

ICML 2021 On Energy-Based Models with Overparametrized Shallow Neural Networks Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna

ICLR 2021 On Graph Neural Networks Versus Graph-Augmented MLPs Lei Chen, Zhengdao Chen, Joan Bruna

NeurIPS 2021 On the Cryptographic Hardness of Learning Single Periodic Neurons Min Jae Song, Ilias Zadik, Joan Bruna

NeurIPS 2021 On the Sample Complexity of Learning Under Geometric Stability Alberto Bietti, Luca Venturi, Joan Bruna

NeurIPS 2020 A Dynamical Central Limit Theorem for Shallow Neural Networks Zhengdao Chen, Grant Rotskoff, Joan Bruna, Eric Vanden-Eijnden

NeurIPS 2020 A Mean-Field Analysis of Two-Player Zero-Sum Games Carles Domingo-Enrich, Samy Jelassi, Arthur Mensch, Grant Rotskoff, Joan Bruna

NeurIPS 2020 Can Graph Neural Networks Count Substructures? Zhengdao Chen, Lei Chen, Soledad Villar, Joan Bruna

ICML 2020 Extra-Gradient with Player Sampling for Faster Convergence in N-Player Games Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna

ICLR 2020 Geometric Insights into the Convergence of Nonlinear TD Learning David Brandfonbrener, Joan Bruna

NeurIPS 2020 IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gurbuzbalaban, Stefanie Jegelka, Hongzhou Lin

MLOSS 2020 Kymatio: Scattering Transforms in Python 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 Cella, Michael Eickenberg

UAI 2020 Provably Efficient Third-Person Imitation from Offline Observation Aaron Zweig, Joan Bruna

ICLR 2020 Pure and Spurious Critical Points: A Geometric Study of Linear Networks Matthew Trager, Kathlén Kohn, Joan Bruna

ICML 2019 Approximating Orthogonal Matrices with Effective Givens Factorization Thomas Frerix, Joan Bruna

ICLR 2019 Diffusion Scattering Transforms on Graphs Fernando Gama, Alejandro Ribeiro, Joan Bruna

NeurIPS 2019 Finding the Needle in the Haystack with Convolutions: On the Benefits of Architectural Bias Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Joan Bruna

NeurIPS 2019 Gradient Dynamics of Shallow Univariate ReLU Networks Francis Williams, Matthew Trager, Daniele Panozzo, Claudio Silva, Denis Zorin, Joan Bruna

ICML 2019 Neuron Birth-Death Dynamics Accelerates Gradient Descent and Converges Asymptotically Grant Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden

NeurIPS 2019 On the Equivalence Between Graph Isomorphism Testing and Function Approximation with GNNs Zhengdao Chen, Soledad Villar, Lei Chen, Joan Bruna

NeurIPS 2019 On the Expressive Power of Deep Polynomial Neural Networks Joe Kileel, Matthew Trager, Joan Bruna

JMLR 2019 Spurious Valleys in One-Hidden-Layer Neural Network Optimization Landscapes Luca Venturi, Afonso S. Bandeira, Joan Bruna

NeurIPS 2019 Stability of Graph Scattering Transforms Fernando Gama, Alejandro Ribeiro, Joan Bruna

ICLR 2019 Supervised Community Detection with Line Graph Neural Networks Zhengdao Chen, Lisha Li, Joan Bruna

ICLR 2018 Divide and Conquer Networks Alex Nowak, David Folqué, Joan Bruna

ICLR 2017 Topology and Geometry of Half-Rectified Network Optimization C. Daniel Freeman, Joan Bruna

ICLR 2017 Understanding Trainable Sparse Coding with Matrix Factorization Thomas Moreau, Joan Bruna

ICLR 2016 Super-Resolution with Deep Convolutional Sufficient Statistics Joan Bruna, Pablo Sprechmann, Yann LeCun

ICLR 2015 Audio Source Separation with Discriminative Scattering Networks Pablo Sprechmann, Joan Bruna, Yann LeCun

ICLR 2015 Unsupervised Feature Learning from Temporal Data Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

ICCV 2015 Unsupervised Learning of Spatiotemporally Coherent Metrics Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

NeurIPS 2014 Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation Emily L Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus

ICLR 2014 Intriguing Properties of Neural Networks Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, Rob Fergus

ICLR 2014 Spectral Networks and Locally Connected Networks on Graphs Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun

ICLR 2013 Learning Stable Group Invariant Representations with Convolutional Networks Joan Bruna, Arthur Szlam, Yann LeCun

CVPR 2011 Classification with Scattering Operators Joan Bruna, Stéphane Mallat