approximation theory

Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem ICLR 2020 Frequency-based Search-control in Dyna ICLR 2020 Neural Networks with Small Weights and Depth-Separation Barriers NeurIPS 2020 Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions NeurIPS 2020 Sharp Representation Theorems for ReLU Networks with Precise Dependence on Depth NeurIPS 2020 Towards Adaptive Residual Network Training: A Neural-ODE Perspective ICML 2020 Universal Approximation with Deep Narrow Networks COLT 2020 Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality ICLR 2019 Approximation and non-parametric estimation of ResNet-type convolutional neural networks ICML 2019 Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds NeurIPS 2019 Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability AISTATS 2019 On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks ICLR 2019 The Comparative Power of ReLU Networks and Polynomial Kernels in the Presence of Sparse Latent Structure ICLR 2019 Universal Approximation of Input-Output Maps by Temporal Convolutional Nets NeurIPS 2019 A Spline Theory of Deep Learning ICML 2018 Bounds on the Approximation Power of Feedforward Neural Networks ICML 2018 Depth Separation for Neural Networks COLT 2017 Neural Networks and Rational Functions ICML 2017 On the Ability of Neural Nets to Express Distributions COLT 2017 benefits of depth in neural networks COLT 2016 The Power of Depth for Feedforward Neural Networks COLT 2016 Optimal Rates for Random Fourier Features NeurIPS 2015 Compressed Hashing CVPR 2013 Discussion of “A conditional game for comparing approximations” AISTATS 2011 The Tradeoffs of Large Scale Learning NeurIPS 2007