Boris Hanin

Nonlinear Approximation and (Deep) $$\mathrm {ReLU}$$ Networks

Ingrid Daubechies, Ronald DeVore, Simon Foucart et al. · Constructive Approximation · 2021 · 183 citations

Engineering, Nonlinear Approximation, Deep Learning +2

Approximating Continuous Functions by ReLU Nets of Minimal Width

Boris Hanin, Mark Sellke · arXiv (Cornell University) · 2017 · 142 citations · Full text

Mathematical Programming, Layer Widths, Neural Scaling Law +14

Nonlinear Approximation and (Deep) ReLU Networks

Ingrid Daubechies, Ronald DeVore, Simon Foucart et al. · arXiv (Cornell University) · 2019 · 104 citations · Full text

Geometric Learning, Deep Neural Networks, Engineering +13

Complexity of Linear Regions in Deep Networks

Boris Hanin, David Rolnick · arXiv (Cornell University) · 2019 · 54 citations · Full text

Geometric Learning, Convolutional Neural Network, Engineering +15

Products of Many Large Random Matrices and Gradients in Deep Neural Networks

Boris Hanin, Mihai Nica · Communications in Mathematical Physics · 2019 · 53 citations · Full text

Deep Neural Networks, Engineering, Machine Learning +6