Search Results for author:
Found 24 papers, 13 papers with code
Leveraging Cardiovascular Simulations for In-Vivo Prediction of Cardiac Biomarkers
Whole-body hemodynamics simulators, which model blood flow and pressure waveforms as functions of physiological parameters, are now essential tools for studying cardiovascular systems.
Considerations for Distribution Shift Robustness of Diagnostic Models in Healthcare
We consider robustness to distribution shifts in the context of diagnostic models in healthcare, where the prediction target $Y$, e. g., the presence of a disease, is causally upstream of the observations $X$, e. g., a biomarker.
Addressing Misspecification in Simulation-based Inference through Data-driven Calibration
Driven by steady progress in generative modeling, simulation-based inference (SBI) has enabled inference over stochastic simulators.
Simulation-based Inference for Cardiovascular Models
Over the past decades, hemodynamics simulators have steadily evolved and have become tools of choice for studying cardiovascular systems in-silico.
Robust Hybrid Learning With Expert Augmentation
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data.
Learning Invariant Representations with Missing Data
Enforcing such independencies requires nuisances to be observed during training.
Environment Inference for Invariant Learning
Learning models that gracefully handle distribution shifts is central to research on domain generalization, robust optimization, and fairness.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Understanding and Mitigating Exploding Inverses in Invertible Neural Networks
For problems where global invertibility is necessary, such as applying normalizing flows on OOD data, we show the importance of designing stable INN building blocks.
Shortcut Learning in Deep Neural Networks
Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today's machine intelligence.
Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
Adversarial examples are malicious inputs crafted to induce misclassification.
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
Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y).
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks
Our BCOP parameterization allows us to train large convolutional networks with provable Lipschitz bounds.
On the Invertibility of Invertible Neural Networks
Guarantees in deep learning are hard to achieve due to the interplay of flexible modeling schemes and complex tasks.
Flexibly Fair Representation Learning by Disentanglement
We consider the problem of learning representations that achieve group and subgroup fairness with respect to multiple sensitive attributes.
Residual Flows for Invertible Generative Modeling
Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood.
Ranked #2 on
Image Generation
on MNIST
Understanding the Limitations of Conditional Generative Models
Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts.
Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
Excessive invariance is not limited to models trained to be robust to perturbation-based $\ell_p$-norm adversaries.
Invertible Residual Networks
We show that standard ResNet architectures can be made invertible, allowing the same model to be used for classification, density estimation, and generation.
Ranked #5 on
Image Generation
on MNIST
Excessive Invariance Causes Adversarial Vulnerability
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs.
i-RevNet: Deep Invertible Networks
An analysis of i-RevNets learned representations suggests an alternative explanation for the success of deep networks by a progressive contraction and linear separation with depth.
Dynamic Steerable Blocks in Deep Residual Networks
Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account.
Multiscale Hierarchical Convolutional Networks
Multiscale hierarchical convolutional networks are structured deep convolutional networks where layers are indexed by progressively higher dimensional attributes, which are learned from training data.
Structured Receptive Fields in CNNs
We combine these ideas into structured receptive field networks, a model which has a fixed filter basis and yet retains the flexibility of CNNs.
