Search Results for author:
Found 10 papers, 4 papers with code
Out-of-Distribution Detection Should Use Conformal Prediction (and Vice-versa?)
Based on the work of (Bates et al., 2022), we define new conformal AUROC and conformal FRP@TPR95 metrics, which are corrections that provide probabilistic conservativeness guarantees on the variability of these metrics.
GROOD: GRadient-aware Out-Of-Distribution detection in interpolated manifolds
To build this space, GROOD relies on class prototypes together with a prototype that specifically captures OOD characteristics.
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks.
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against $l2$ adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms.
Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees)
To tackle this trade-off, we design a hybrid simulation code coupling a traditional fluid dynamic solver with a neural network approximating the chemical reactions.
Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning
In this work, we study the use of goal-oriented sensitivity analysis, based on the Hilbert-Schmidt Independence Criterion (HSIC), for hyperparameter analysis and optimization.
Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure
HSIC measures the dependence between regions of an input image and the output of a model based on kernel embeddings of distributions.
A Taylor Based Sampling Scheme for Machine Learning in Computational Physics
Machine Learning (ML) is increasingly used to construct surrogate models for physical simulations.
Leveraging Local Variation in Data: Sampling and Weighting Schemes for Supervised Deep Learning
In the context of supervised learning of a function by a neural network, we claim and empirically verify that the neural network yields better results when the distribution of the data set focuses on regions where the function to learn is steep.
Variance Based Sample Weighting for Supervised Learning
In the context of supervised learning of a function by a Neural Network (NN), we claim and empirically justify that a NN yields better results when the distribution of the data set focuses on regions where the function to learn is steeper.
