b'Lars Ruthotto'

research

∙ 05/31/2023

Alternating Minimization for Regression with Tropical Rational Functions

We propose an alternating minimization heuristic for regression over the...

0 Alex Dunbar, et al. ∙

research

∙ 03/08/2023

Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation

Score-based diffusion models (SBDM) have recently emerged as state-of-th...

0 Paul Hagemann, et al. ∙

research

∙ 10/31/2022

ωGNNs: Deep Graph Neural Networks Enhanced by Multiple Propagation Operators

Graph Neural Networks (GNNs) are limited in their propagation operators....

0 Moshe Eliasof, et al. ∙

research

∙ 02/23/2022

Multivariate Quantile Function Forecaster

We propose Multivariate Quantile Function Forecaster (MQF^2), a global p...

0 Kelvin Kan, et al. ∙

research

∙ 09/28/2021

slimTrain – A Stochastic Approximation Method for Training Separable Deep Neural Networks

Deep neural networks (DNNs) have shown their success as high-dimensional...

0 Elizabeth Newman, et al. ∙

research

∙ 03/09/2021

An Introduction to Deep Generative Modeling

Deep generative models (DGM) are neural networks with many hidden layers...

100 Lars Ruthotto, et al. ∙

research

∙ 12/11/2020

Avoiding The Double Descent Phenomenon of Random Feature Models Using Hybrid Regularization

We demonstrate the ability of hybrid regularization methods to automatic...

0 Kelvin Kan, et al. ∙

research

∙ 11/17/2020

Multigrid-in-Channels Neural Network Architectures

We present a multigrid-in-channels (MGIC) approach that tackles the quad...

0 Moshe Eliasof, et al. ∙

research

∙ 07/26/2020

Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection

Deep neural networks (DNNs) have achieved state-of-the-art performance a...

11 Elizabeth Newman, et al. ∙

research

∙ 06/11/2020

Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks

We present a multigrid approach that combats the quadratic growth of the...

0 Jonathan Ephrath, et al. ∙

research

∙ 05/29/2020

OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport

A normalizing flow is an invertible mapping between an arbitrary probabi...

15 Derek Onken, et al. ∙

research

∙ 05/27/2020

PNKH-B: A Projected Newton-Krylov Method for Large-Scale Bound-Constrained Optimization

We present PNKH-B, a projected Newton-Krylov method with a low-rank appr...

0 Kelvin Kan, et al. ∙

research

∙ 05/27/2020

Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing Flows

We compare the discretize-optimize (Disc-Opt) and optimize-discretize (O...

20 Derek Onken, et al. ∙

research

∙ 02/15/2020

A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems

Mean field games (MFG) and mean field control (MFC) are critical classes...

0 Lars Ruthotto, et al. ∙

research

∙ 10/29/2019

LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have become indispensable for solvi...

29 Jonathan Ephrath, et al. ∙

research

∙ 04/15/2019

LeanResNet: A Low-cost yet Effective Convolutional Residual Networks

Convolutional Neural Networks (CNNs) filter the input data using a serie...

0 Jonathan Ephrath, et al. ∙

research

∙ 03/06/2019

IMEXnet: A Forward Stable Deep Neural Network

Deep convolutional neural networks have revolutionized many machine lear...

0 Eldad Haber, et al. ∙

research

∙ 01/27/2019

Large-Scale Classification using Multinomial Regression and ADMM

We present a novel method for learning the weights in multinomial logist...

0 Samy Wu Fung, et al. ∙

research

∙ 05/21/2018

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 derivative-free optimization method and i...

0 Eldad Haber, et al. ∙

research

∙ 05/21/2018

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 derivative-free optimization method and i...

0 Eldad Haber, et al. ∙

research

∙ 05/20/2018

Low-Cost Parameterizations of Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) filter the input data using a serie...

0 Eran Treister, et al. ∙

research

∙ 05/20/2018

Low-Cost Parameterizations of Deep Convolution Neural Networks

The main computational cost in the training of and prediction with Convo...

0 Eran Treister, et al. ∙

research

∙ 04/12/2018

Deep Neural Networks motivated by Partial Differential Equations

Partial differential equations (PDEs) are indispensable for modeling man...

0 Lars Ruthotto, et al. ∙

research

∙ 03/07/2018

A Bayesian framework for molecular strain identification from mixed diagnostic samples

We provide a mathematical formulation and develop a computational framew...

0 Lauri Mustonen, et al. ∙

research

∙ 09/12/2017

Reversible Architectures for Arbitrarily Deep Residual Neural Networks

Recently, deep residual networks have been successfully applied in many ...

0 Bo Chang, et al. ∙

research

∙ 05/28/2017

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...

0 James Herring, et al. ∙

research

∙ 05/09/2017

Stable Architectures for Deep Neural Networks

Deep neural networks have become invaluable tools for supervised machine...

0 Eldad Haber, et al. ∙

research

∙ 03/13/2017

A Lagrangian Gauss-Newton-Krylov Solver for Mass- and Intensity-Preserving Diffeomorphic Image Registration

We present an efficient solver for diffeomorphic image registration prob...

0 Andreas Mang, et al. ∙

research

∙ 03/06/2017

Learning across scales - A multiscale method for Convolution Neural Networks

In this work we establish the relation between optimal control and train...

0 Eldad Haber, et al. ∙

research

∙ 06/23/2016

jInv -- a flexible Julia package for PDE parameter estimation

Estimating parameters of Partial Differential Equations (PDEs) from nois...

0 Lars Ruthotto, et al. ∙

Lars Ruthotto

Featured Co-authors