Theory

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs NeurIPS 2023 Learning Curves for Deep Structured Gaussian Feature Models NeurIPS 2023 Learning Layer-wise Equivariances Automatically using Gradients NeurIPS 2023 Lie Point Symmetry and Physics-Informed Networks NeurIPS 2023 Limitless Stability for Graph Convolutional Networks ICLR 2023 Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies ICML 2023 Local Intrinsic Dimensional Entropy AAAI 2023 Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes ICLR 2023 Machines of Finite Depth: Towards a Formalization of Neural Networks AAAI 2023 Manifold-Preserving Transformers are Effective for Short-Long Range Encoding EMNLP 2023 Maximal Initial Learning Rates in Deep ReLU Networks ICML 2023 Maximum likelihood estimation in Gaussian process regression is ill-posed JMLR 2023 Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence ICLR 2023 Memorisation Cartography: Mapping out the Memorisation-Generalisation Continuum in Neural Machine Translation EMNLP 2023 Minimum Width of Leaky-ReLU Neural Networks for Uniform Universal Approximation ICML 2023 ModelDiff: A Framework for Comparing Learning Algorithms ICML 2023 Most Neural Networks Are Almost Learnable NeurIPS 2023 Nearly-tight Bounds for Deep Kernel Learning ICML 2023 Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective ICML 2023 Neural networks trained with SGD learn distributions of increasing complexity ICML 2023 Neural Oscillators are Universal NeurIPS 2023 Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks AAAI 2023 Neural signature kernels as infinite-width-depth-limits of controlled ResNets ICML 2023 Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think ICML 2023 Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities ICLR 2023