approximation theory

Learning with convolution and pooling operations in kernel methods NeurIPS 2022 Neural Network Architecture Beyond Width and Depth NeurIPS 2022 On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NeurIPS 2022 On the approximation properties of recurrent encoder-decoder architectures ICLR 2022 Size and depth of monotone neural networks: interpolation and approximation NeurIPS 2022 Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers NeurIPS 2022 Theoretically Provable Spiking Neural Networks NeurIPS 2022 Tighter Sparse Approximation Bounds for ReLU Neural Networks ICLR 2022 A Functional Perspective on Learning Symmetric Functions with Neural Networks ICML 2021 Approximation Theory Based Methods for RKHS Bandits ICML 2021 Approximation Theory of Convolutional Architectures for Time Series Modelling ICML 2021 BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation NeurIPS 2021 Deep Equals Shallow for ReLU Networks in Kernel Regimes ICLR 2021 Efficient Interpolation of Density Estimators AISTATS 2021 Large-Scale Learning with Fourier Features and Tensor Decompositions NeurIPS 2021 Minimum Width for Universal Approximation ICLR 2021 On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis ICLR 2021 On the Universality of Graph Neural Networks on Large Random Graphs NeurIPS 2021 On the Universality of Rotation Equivariant Point Cloud Networks ICLR 2021 Parametric Complexity Bounds for Approximating PDEs with Neural Networks NeurIPS 2021 PSD Representations for Effective Probability Models NeurIPS 2021 Towards a Unified Analysis of Random Fourier Features JMLR 2021 Training deep residual networks for uniform approximation guarantees L4DC 2021 A closer look at the approximation capabilities of neural networks ICLR 2020 Approximation Capabilities of Neural ODEs and Invertible Residual Networks ICML 2020