research
∙
08/28/2023
Improved learning theory for kernel distribution regression with two-stage sampling
The distribution regression problem encompasses many important statistic...
share
research
∙
06/11/2023
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation
In recent years, concept-based approaches have emerged as some of the mo...
research
∙
05/25/2023
DP-SGD Without Clipping: The Lipschitz Neural Network Way
State-of-the-art approaches for training Differentially Private (DP) Dee...
research
∙
11/17/2022
CRAFT: Concept Recursive Activation FacTorization for Explainability
Attribution methods are a popular class of explainability methods that u...
research
∙
10/13/2022
Efficient circuit implementation for coined quantum walks on binary trees and application to reinforcement learning
Quantum walks on binary trees are used in many quantum algorithms to ach...
research
∙
10/12/2022
Gaussian Processes on Distributions based on Regularized Optimal Transport
We present a novel kernel over the space of probability measures based o...
research
∙
06/14/2022
When adversarial attacks become interpretable counterfactual explanations
We argue that, when learning a 1-Lipschitz neural network with the dual ...
research
∙
06/09/2022
Xplique: A Deep Learning Explainability Toolbox
Today's most advanced machine-learning models are hardly scrutable. The ...
research
∙
02/16/2022
GAN Estimation of Lipschitz Optimal Transport Maps
This paper introduces the first statistically consistent estimator of th...
research
∙
04/11/2021
The Many Faces of 1-Lipschitz Neural Networks
Lipschitz constrained models have been used to solve specifics deep lear...
research
∙
11/25/2020
Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
Measuring the generalization performance of a Deep Neural Network (DNN) ...
research
∙
07/08/2020
Predicting the Accuracy of a Few-Shot Classifier
In the context of few-shot learning, one cannot measure the generalizati...
research
∙
07/07/2020
