activity
20172021
most citedNonlinear Approximation and (Deep) ReLU Networks

102 citations · 157 across the 6 of their papers we have counts for

collaborators

16 papers

stat.ML2021

Ridgeless Interpolation with Shallow ReLU Networks in is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions

Boris Hanin

We prove a precise geometric description of all one layer ReLU networks with a single linear unit and input/output dimensions equal to one that interpolate a given dataset…

math.PR2021

Random Neural Networks in the Infinite Width Limit as Gaussian Processes

Boris Hanin

This article gives a new proof that fully connected neural networks with random weights and biases converge to Gaussian processes in the regime where the input dimension, output di…

stat.ML2021

Deep ReLU Networks Preserve Expected Length

Boris Hanin, Ryan Jeong, David Rolnick

Assessing the complexity of functions computed by a neural network helps us understand how the network will learn and generalize. One natural measure of complexity is how the netwo…

math.NA2020

Neural Network Approximation

Ronald DeVore, Boris Hanin, Guergana Petrova

Neural Networks (NNs) are the method of choice for building learning algorithms. Their popularity stems from their empirical success on several challenging learning problems. Howev…

cs.LG2020

How Data Augmentation affects Optimization for Linear Regression

Boris Hanin, Yi Sun

Though data augmentation has rapidly emerged as a key tool for optimization in modern machine learning, a clear picture of how augmentation schedules affect optimization and intera…

math.PR2020

Non-asymptotic Results for Singular Values of Gaussian Matrix Products

Boris Hanin, Grigoris Paouris

This article concerns the non-asymptotic analysis of the singular values (and Lyapunov exponents) of Gaussian matrix products in the regime where the number of term in the pro…