Joern-Henrik Jacobsen — accepted AI-conference papers

2025

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

Antoine Wehenkel, Juan L. Gamella, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Joern-Henrik Jacobsen +1

ICML 2025oral

Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the parameters of stochastic simulators. However, recent work has demonstrated that model misspecification can harm SBI's reliability, preventing its adoption in importa…

Cited by 12 Source ↗PDF ↗Scholar ↗

2021

Environment Inference for Invariant Learning

Elliot Creager, Joern-Henrik Jacobsen, Richard Zemel

ICML 2021spotlight

Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness. A promising formulation is domain-invariant learning, which identifies the key issue of learning which features are domain-specific versus domain-invariant.…

Cited by 460 Source ↗PDF ↗code ↗Scholar ↗

2021

Out-of-Distribution Generalization via Risk Extrapolation (REx)

David Krueger, Ethan Caballero, Joern-Henrik Jacobsen, Amy Zhang, Jonathan Binas, Dinghuai Zhang +2

ICML 2021oral

Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts a…

Cited by 1103 Source ↗PDF ↗code ↗Scholar ↗

2021

Understanding and Mitigating Exploding Inverses in Invertible Neural Networks

Jens Behrmann, Paul Vicol, Kuan-Chieh Wang, Roger Grosse, Joern-Henrik Jacobsen

AISTATS 2021poster

Invertible neural networks (INNs) have been used to design generative models, implement memory-saving gradient computation, and solve inverse problems. In this work, we show that commonly-used INN architectures suffer from exploding inverses and are thus prone to becoming numerically non-invertible.…

Cited by 122 Source ↗PDF ↗code ↗Scholar ↗

2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Florian Tramer, Jens Behrmann, Nicholas Carlini, Nicolas Papernot, Joern-Henrik Jacobsen

ICML 2020poster

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied \emph{sensitivity-based} adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, \emph{invarianc…

Cited by 111 Source ↗PDF ↗code ↗Scholar ↗

2020

How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization

Chris Finlay, Joern-Henrik Jacobsen, Levon Nurbekyan, Adam Oberman

ICML 2020poster

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 practice this leads to dynamics equivalent to many hundreds or even thousands of layers. In this paper, we overcome this a…

Cited by 296 Source ↗PDF ↗Scholar ↗

2020

Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling

Will Grathwohl, Kuan-Chieh Wang, Joern-Henrik Jacobsen, David Duvenaud, Richard Zemel

ICML 2020poster

We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model’s log-density. We estimate the Stein discrepancy between the data density p(x) and the model density q(x) based on a vector function of the dat…

Cited by 104 Source ↗PDF ↗code ↗Scholar ↗

2020

Understanding the Limitations of Conditional Generative Models

Ethan Fetaya, Joern-Henrik Jacobsen, Will Grathwohl, Richard Zemel

ICLR 2020poster

Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts. They are a natural choice to solve discriminative tasks in a robust manner as they jointly optimize for predictive performance and accurate modeling of the input distribution. In this…

Cited by 59 Source ↗Scholar ↗

2020

Your classifier is secretly an energy based model and you should treat it like one

Will Grathwohl, Kuan-Chieh Wang, Joern-Henrik Jacobsen, David Duvenaud, Mohammad Norouzi, Kevin Swersky

ICLR 2020talk

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x, y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discrimina…

Cited by 674 Source ↗code ↗Scholar ↗

2019

Excessive Invariance Causes Adversarial Vulnerability

Joern-Henrik Jacobsen, Jens Behrmann, Richard Zemel, Matthias Bethge

ICLR 2019poster

Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity a…

Cited by 201 Source ↗PDF ↗Scholar ↗

2019

Flexibly Fair Representation Learning by Disentanglement

Elliot Creager, David Madras, Joern-Henrik Jacobsen, Marissa Weis, Kevin Swersky, Toniann Pitassi +1

ICML 2019oral

We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes. Taking inspiration from the disentangled representation learning literature, we propose an algorithm for learning compact representations of datasets that are u…

Cited by 430 Source ↗PDF ↗code ↗Scholar ↗

2019

Invertible Residual Networks

Jens Behrmann, Will Grathwohl, Ricky T. Q. Chen, David Duvenaud, Joern-Henrik Jacobsen

ICML 2019oral

We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation. Typically, enforcing invertibility requires partitioning dimensions or restricting network architectures. In contrast, our approach only requi…

Cited by 759 Source ↗PDF ↗Scholar ↗

2019

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

Qiyang Li, Saminul Haque, Cem Anil, James Lucas, Roger B Grosse, Joern-Henrik Jacobsen

NeurIPS 2019poster

Lipschitz constraints under L2 norm on deep neural networks are useful for provable adversarial robustness bounds, stable training, and Wasserstein distance estimation. While heuristic approaches such as the gradient penalty have seen much practical success, it is challenging to achieve similar prac…

Cited by 123 Source ↗PDF ↗code ↗Scholar ↗

2019

Residual Flows for Invertible Generative Modeling

Ricky T. Q. Chen, Jens Behrmann, David K. Duvenaud, Joern-Henrik Jacobsen

NeurIPS 2019spotlight

Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only Lipschitz conditions rather than strict architectural constraints ar…

Cited by 451 Source ↗PDF ↗code ↗Scholar ↗