397 citations · 968 across the 32 of their papers we have counts for
8 papers · 1 filter
Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid Regularization
Kelvin Kan, James G Nagy, Lars Ruthotto
We demonstrate the ability of hybrid regularization methods to automatically avoid the double descent phenomenon arising in the training of random feature models (RFM). The hallmar…
MGIC: Multigrid-in-Channels Neural Network Architectures
Moshe Eliasof, Jonathan Ephrath, Lars Ruthotto +1
We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional ne…
A Neural Network Approach Applied to Multi-Agent Optimal Control
Derek Onken, Levon Nurbekyan, Xingjian Li +3
We propose a neural network approach for solving high-dimensional optimal control problems. In particular, we focus on multi-agent control problems with obstacle and collision avoi…
Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
Elizabeth Newman, Lars Ruthotto, Joseph Hart +1
Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and s…
Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks
Jonathan Ephrath, Lars Ruthotto, Eran Treister
We present a multigrid approach that combats the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs…
OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport
Derek Onken, Samy Wu Fung, Xingjian Li +1
A normalizing flow is an invertible mapping between an arbitrary probability distribution and a standard normal distribution; it can be used for density estimation and statistical…