109 citations · 522 across the 51 of their papers we have counts for
54 papers
Avoiding unsafe sets when training with Langevin Dynamics
Adam M. Oberman
Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics, and a natural safety question is to bound the probability $ν_t(\mathcal{A}_H) = \math…
Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization
Adam M. Oberman
Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretical explanation. We provide o…
EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
Xinlin Li, Mariana Parazeres, Adam Oberman +3
With the advent of deep learning application on edge devices, researchers actively try to optimize their deployments on low-power and restricted memory devices. There are establish…
Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
Vikram Voleti, Christopher Pal, Adam Oberman
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural g…
On the Generalization of Representations in Reinforcement Learning
Charline Le Lan, Stephen Tu, Adam Oberman +2
In reinforcement learning, state representations are used to tractably deal with large problem spaces. State representations serve both to approximate the value function with few p…
Multi-Resolution Continuous Normalizing Flows
Vikram Voleti, Chris Finlay, Adam Oberman +1
Recent work has shown that Neural Ordinary Differential Equations (ODEs) can serve as generative models of images using the perspective of Continuous Normalizing Flows (CNFs). Such…
Frustratingly Easy Uncertainty Estimation for Distribution Shift
Tiago Salvador, Vikram Voleti, Alexander Iannantuono +1
Distribution shift is an important concern in deep image classification, produced either by corruption of the source images, or a complete change, with the solution involving domai…
FairCal: Fairness Calibration for Face Verification
Tiago Salvador, Stephanie Cairns, Vikram Voleti +2
Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the…
Adversarial Boot Camp: label free certified robustness in one epoch
Ryan Campbell, Chris Finlay, Adam M Oberman
Machine learning models are vulnerable to adversarial attacks. One approach to addressing this vulnerability is certification, which focuses on models that are guaranteed to be rob…
Deterministic Gaussian Averaged Neural Networks
Ryan Campbell, Chris Finlay, Adam M Oberman
We present a deterministic method to compute the Gaussian average of neural networks used in regression and classification. Our method is based on an equivalence between training w…
Learning normalizing flows from Entropy-Kantorovich potentials
Chris Finlay, Augusto Gerolin, Adam M Oberman +1
We approach the problem of learning continuous normalizing flows from a dual perspective motivated by entropy-regularized optimal transport, in which continuous normalizing flows a…
How to train your neural ODE: the world of Jacobian and kinetic regularization
Chris Finlay, Jörn-Henrik Jacobsen, Levon Nurbekyan +1
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. In pr…
No-collision Transportation Maps
Levon Nurbekyan, Alexander Iannantuono, Adam M. Oberman
Transportation maps between probability measures are critical objects in numerous areas of mathematics and applications such as PDE, fluid mechanics, geometry, machine learning, co…
Farkas layers: don't shift the data, fix the geometry
Aram-Alexandre Pooladian, Chris Finlay, Adam M Oberman
Successfully training deep neural networks often requires either batch normalization, appropriate weight initialization, both of which come with their own challenges. We propose an…
Partial differential equation regularization for supervised machine learning
Adam M Oberman
This article is an overview of supervised machine learning problems for regression and classification. Topics include: kernel methods, training by stochastic gradient descent, deep…
Nesterov's method with decreasing learning rate leads to accelerated stochastic gradient descent
Maxime Laborde, Adam M. Oberman
We present a coupled system of ODEs which, when discretized with a constant time step/learning rate, recovers Nesterov's accelerated gradient descent algorithm. The same ODEs, when…
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
Aram-Alexandre Pooladian, Chris Finlay, Tim Hoheisel +1
Deep neural networks perform well on real world data but are prone to adversarial perturbations: small changes in the input easily lead to misclassification. In this work, we propo…
A Partial Differential Equation Obstacle Problem for the Level Set Approach to Visibility
Adam Oberman, Tiago Salvador
In this article we consider the problem of finding the visibility set from a given point when the obstacles are represented as the level set of a given function. Although the visib…
Scaleable input gradient regularization for adversarial robustness
Chris Finlay, Adam M Oberman
In this work we revisit gradient regularization for adversarial robustness with some new ingredients. First, we derive new per-image theoretical robustness bounds based on local gr…
The LogBarrier adversarial attack: making effective use of decision boundary information
Chris Finlay, Aram-Alexandre Pooladian, Adam M. Oberman
Adversarial attacks for image classification are small perturbations to images that are designed to cause misclassification by a model. Adversarial attacks formally correspond to a…
Calibrated Top-1 Uncertainty estimates for classification by score based models
Adam M. Oberman, Chris Finlay, Alexander Iannantuono +1
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 th…
Stochastic Gradient Descent with Polyak's Learning Rate
Adam M. Oberman, Mariana Prazeres
Stochastic gradient descent (SGD) for strongly convex functions converges at the rate $\bO(1/k)$. However, achieving good results in practice requires tuning the parameters (for ex…
Improved robustness to adversarial examples using Lipschitz regularization of the loss
Chris Finlay, Adam Oberman, Bilal Abbasi
We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_…
Lipschitz regularized Deep Neural Networks generalize and are adversarially robust
Chris Finlay, Jeff Calder, Bilal Abbasi +1
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robust…