
An Introduction to Deep Generative Modeling
Deep generative models (DGM) are neural networks with many hidden layers...
read it

Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid Regularization
We demonstrate the ability of hybrid regularization methods to automatic...
read it

MultigridinChannels Neural Network Architectures
We present a multigridinchannels (MGIC) approach that tackles the quad...
read it

Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
Deep neural networks (DNNs) have achieved stateoftheart performance a...
read it

MultigridinChannels Architectures for Wide Convolutional Neural Networks
We present a multigrid approach that combats the quadratic growth of the...
read it

OTFlow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport
A normalizing flow is an invertible mapping between an arbitrary probabi...
read it

PNKHB: A Projected NewtonKrylov Method for LargeScale BoundConstrained Optimization
We present PNKHB, a projected NewtonKrylov method with a lowrank appr...
read it

DiscretizeOptimize vs. OptimizeDiscretize for TimeSeries Regression and Continuous Normalizing Flows
We compare the discretizeoptimize (DiscOpt) and optimizediscretize (O...
read it

A Machine Learning Framework for Solving HighDimensional Mean Field Game and Mean Field Control Problems
Mean field games (MFG) and mean field control (MFC) are critical classes...
read it

LeanConvNets: Lowcost Yet Effective Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have become indispensable for solvi...
read it

LeanResNet: A Lowcost yet Effective Convolutional Residual Networks
Convolutional Neural Networks (CNNs) filter the input data using a serie...
read it

IMEXnet: A Forward Stable Deep Neural Network
Deep convolutional neural networks have revolutionized many machine lear...
read it

LargeScale Classification using Multinomial Regression and ADMM
We present a novel method for learning the weights in multinomial logist...
read it

Never look back  A modified EnKF method and its application to the training of neural networks without back propagation
In this work, we present a new derivativefree optimization method and i...
read it

Never look back  The EnKF method and its application to the training of neural networks without back propagation
In this work, we present a new derivativefree optimization method and i...
read it

LowCost Parameterizations of Deep Convolutional Neural Networks
Convolutional Neural Networks (CNNs) filter the input data using a serie...
read it

LowCost Parameterizations of Deep Convolution Neural Networks
The main computational cost in the training of and prediction with Convo...
read it

Deep Neural Networks motivated by Partial Differential Equations
Partial differential equations (PDEs) are indispensable for modeling man...
read it

A Bayesian framework for molecular strain identification from mixed diagnostic samples
We provide a mathematical formulation and develop a computational framew...
read it

Reversible Architectures for Arbitrarily Deep Residual Neural Networks
Recently, deep residual networks have been successfully applied in many ...
read it

LAP: a Linearize and Project Method for Solving Inverse Problems with Coupled Variables
Many inverse problems involve two or more sets of variables that represe...
read it

Stable Architectures for Deep Neural Networks
Deep neural networks have become invaluable tools for supervised machine...
read it

A Lagrangian GaussNewtonKrylov Solver for Mass and IntensityPreserving Diffeomorphic Image Registration
We present an efficient solver for diffeomorphic image registration prob...
read it

Learning across scales  A multiscale method for Convolution Neural Networks
In this work we establish the relation between optimal control and train...
read it

jInv  a flexible Julia package for PDE parameter estimation
Estimating parameters of Partial Differential Equations (PDEs) from nois...
read it
Lars Ruthotto
verfied profile