Concept
Dimensional regularization
Related publications (32)
Flux correlators and semiclassics
Riccardo Rattazzi, Alexander Monin, Eren Clément Firat, Matthew Thomas Walters
We consider correlators for the flux of energy and charge in the background of operators with large global U(1) charge in conformal field theory (CFT). It has recently been shown that the corresponding Euclidean correlators generically admit a semiclassica ...
Springer2024Efficient local linearity regularization to overcome catastrophic overfitting
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora
Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...
2024Regularization of polynomial networks for image recognition
Volkan Cevher, Grigorios Chrysos, Bohan Wang
Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...
2023Feynman diagrams and the large charge expansion in 3-epsilon dimensions
Riccardo Rattazzi, Alexander Monin, Gil Badel, Gabriel Francisco Cuomo
In arXiv:1909.01269 it was shown that the scaling dimension of the lightest charge n operator in the U (1) model at the Wilson-Fisher fixed point in D = 4 - epsilon can be computed semiclassically for arbitrary values of lambda n, where lambda is the pertu ...
2020Accurate Nod and 3D Gaze Estimation for Social Interaction Analysis
Non-verbal behaviours play an important role in human communication since it can indicate human attention, serve as communication cue in interactions, or even reveal higher level personal constructs. For instance, head nod, a common non-verbal behaviour, c ...
EPFL2020Learning Multi-Label Aerial Image Classification Under Label Noise: A Regularization Approach Using Word Embeddings
Training deep neural networks requires well-annotated datasets. However, real world datasets are often noisy, especially in a multi-label scenario, i.e. where each data point can be attributed to more than one class. To this end, we propose a regularizatio ...
IEEE2020Solving Continuous-Domain Problems Exactly with Multiresolution B-Splines
Michaël Unser, Julien René Pierre Fageot, Harshit Gupta, Thomas Jean Debarre
We propose a discretization method for continuous-domain linear inverse problems with multiple-order total-variation (TV) regularization. It is based on a recent result that proves that such inverse problems have sparse polynomial-spline solutions. Our met ...
IEEE2019