Joan Bruna

Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon COLT 2025 Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos ICML 2025 Quality over Quantity in Attention Layers: When Adding More Heads Hurts ICLR 2025 Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers ICLR 2025 Provable Posterior Sampling with Denoising Oracles via Tilted Transport NIPS 2024 Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract) COLT 2024 Stochastic Optimal Control Matching NIPS 2024 Symmetric Single Index Learning ICLR 2024 Beyond the Edge of Stability via Two-step Gradient Updates ICML 2023 Conditionally Strongly Log-Concave Generative Models ICML 2023 On Single-Index Models beyond Gaussian Data NIPS 2023 A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks NIPS 2023 Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation NIPS 2023 When does return-conditioned supervised learning work for offline reinforcement learning? NIPS 2022 Learning single-index models with shallow neural networks NIPS 2022 On Non-Linear operators for Geometric Deep Learning NIPS 2022 Exponential Separations in Symmetric Neural Networks NIPS 2022 Neural Fields As Learnable Kernels for 3D Reconstruction CVPR 2022 Cartoon Explanations of Image Classifiers ECCV 2022 On feature learning in neural networks with global convergence guarantees ICLR 2022 Depth separation beyond radial functions JMLR 2022 Extended Unconstrained Features Model for Exploring Deep Neural Collapse ICML 2022 Lattice-Based Methods Surpass Sum-of-Squares in Clustering COLT 2022 Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks CVPR 2021 Offline RL Without Off-Policy Evaluation NIPS 2021 On the Sample Complexity of Learning under Geometric Stability NIPS 2021 On the Cryptographic Hardness of Learning Single Periodic Neurons NIPS 2021 A Permutation-Equivariant Neural Network Architecture For Auction Design AAAI 2021 On Graph Neural Networks versus Graph-Augmented MLPs ICLR 2021 Offline Contextual Bandits with Overparameterized Models ICML 2021 On Energy-Based Models with Overparametrized Shallow Neural Networks ICML 2021 A Functional Perspective on Learning Symmetric Functions with Neural Networks ICML 2021 Pure and Spurious Critical Points: a Geometric Study of Linear Networks ICLR 2020 Extra-gradient with player sampling for faster convergence in n-player games ICML 2020 Kymatio: Scattering Transforms in Python JMLR 2020 A Dynamical Central Limit Theorem for Shallow Neural Networks NIPS 2020 Provably Efficient Third-Person Imitation from Offline Observation UAI 2020 IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method NIPS 2020 A mean-field analysis of two-player zero-sum games NIPS 2020 Can Graph Neural Networks Count Substructures? NIPS 2020 Geometric Insights into the Convergence of Nonlinear TD Learning ICLR 2020 Stability of Graph Scattering Transforms NIPS 2019 Deep Geometric Prior for Surface Reconstruction CVPR 2019 Gradient Dynamics of Shallow Univariate ReLU Networks NIPS 2019 Supervised Community Detection with Line Graph Neural Networks ICLR 2019 Diffusion Scattering Transforms on Graphs ICLR 2019 Spurious Valleys in One-hidden-layer Neural Network Optimization Landscapes JMLR 2019 Approximating Orthogonal Matrices with Effective Givens Factorization ICML 2019 Neuron birth-death dynamics accelerates gradient descent and converges asymptotically ICML 2019 Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias NIPS 2019 On the Expressive Power of Deep Polynomial Neural Networks NIPS 2019 On the equivalence between graph isomorphism testing and function approximation with GNNs NIPS 2019 Divide and Conquer Networks ICLR 2018 Surface Networks CVPR 2018 Unsupervised Learning of Spatiotemporally Coherent Metrics ICCV 2015 Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation NIPS 2014