approximation theory

Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NeurIPS 2024 Achieve the Minimum Width of Neural Networks for Universal Approximation ICLR 2023 A Fast, Well-Founded Approximation to the Empirical Neural Tangent Kernel ICML 2023 Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input ICML 2023 Composable Coresets for Determinant Maximization: Greedy is Almost Optimal NeurIPS 2023 How Powerful are Shallow Neural Networks with Bandlimited Random Weights? ICML 2023 Limitations on approximation by deep and shallow neural networks JMLR 2023 Limits, approximation and size transferability for GNNs on sparse graphs via graphops NeurIPS 2023 Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem NeurIPS 2023 On the Connection Between MPNN and Graph Transformer ICML 2023 Operator learning with PCA-Net: upper and lower complexity bounds JMLR 2023 Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces JMLR 2023 Optimal approximation using complex-valued neural networks NeurIPS 2023 A general approximation lower bound in L^p norm, with applications to feed-forward neural networks NeurIPS 2022 Approximation and Optimization Theory for Linear Continuous-Time Recurrent Neural Networks JMLR 2022 Approximation with CNNs in Sobolev Space: with Applications to Classification NeurIPS 2022 A spectral-based analysis of the separation between two-layer neural networks and linear methods JMLR 2022 A Theoretical View on Sparsely Activated Networks NeurIPS 2022 Coin Flipping Neural Networks ICML 2022 Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisited NeurIPS 2022 Deep Network Approximation in Terms of Intrinsic Parameters ICML 2022 Depth separation beyond radial functions JMLR 2022 Efficient learning of sparse and decomposable PDEs using random projection UAI 2022 Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky’s Theorem AISTATS 2022 KAM Theory Meets Statistical Learning Theory: Hamiltonian Neural Networks with Non-zero Training Loss AAAI 2022