Search Results for author:
Found 13 papers, 8 papers with code
Learning normalizing flows from Entropy-Kantorovich potentials
We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows are cast as gradients of scalar potential functions.
Deterministic Gaussian Averaged Neural Networks
We present a deterministic method to compute the Gaussian average of neural networks used in regression and classification.
How to train your neural ODE: the world of Jacobian and kinetic regularization
Training neural ODEs on large datasets has not been tractable due to the necessity of allowing the adaptive numerical ODE solver to refine its step size to very small values.
Ranked #1 on
Density Estimation
on CelebA-HQ 256x256
No-collision Transportation Maps
Transportation maps between probability measures are critical objects in numerous areas of mathematics and applications such as PDE, fluid mechanics, geometry, machine learning, computer science, and economics.
Optimization and Control 49M27,
Farkas layers: don't shift the data, fix the geometry
Successfully training deep neural networks often requires either batch normalization, appropriate weight initialization, both of which come with their own challenges.
Partial differential equation regularization for supervised machine learning
This article is an overview of supervised machine learning problems for regression and classification.
Empirical confidence estimates for classification by deep neural networks
It is well-known that the softmax values of the network are not estimates of the probabilities of class labels.
Scaleable input gradient regularization for adversarial robustness
In this work we revisit gradient regularization for adversarial robustness with some new ingredients.
Lipschitz regularized Deep Neural Networks generalize
We show that if the usual training loss is augmented by a Lipschitz regularization term, then the networks generalize.
The LogBarrier adversarial attack: making effective use of decision boundary information
Adversarial attacks formally correspond to an optimization problem: find a minimum norm image perturbation, constrained to cause misclassification.
Calibrated Top-1 Uncertainty estimates for classification by score based models
While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree.
Stochastic Gradient Descent with Polyak's Learning Rate
We prove convergence at the rate O(1/k) with a rate constant which can be better than the constant for optimally scheduled SGD.
Optimization and Control
Anomaly detection and classification for streaming data using PDEs
We propose in this paper a fast real-time streaming version of the PDA algorithm for anomaly detection that exploits the computational advantages of PDE continuum limits.
