284 citations · 405 across the 19 of their papers we have counts for
19 papers · 1 filter
Generalization Through The Lens Of Leave-One-Out Error
Gregor Bachmann, Thomas Hofmann, Aurélien Lucchi
Despite the tremendous empirical success of deep learning models to solve various learning tasks, our theoretical understanding of their generalization ability is very limited. Cla…
Neural Symbolic Regression that Scales
Luca Biggio, Tommaso Bendinelli, Alexander Neitz +2
Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditio…
Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks
Antonio Orvieto, Jonas Kohler, Dario Pavllo +2
This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks. Leveraging an in-depth analysis of neural chain…
Generative Minimization Networks: Training GANs Without Competition
Paulina Grnarova, Yannic Kilcher, Kfir Y. Levy +2
Many applications in machine learning can be framed as minimization problems and solved efficiently using gradient-based techniques. However, recent applications of generative mode…
Scalable Graph Networks for Particle Simulations
Karolis Martinkus, Aurelien Lucchi, Nathanaël Perraudin
Learning system dynamics directly from observations is a promising direction in machine learning due to its potential to significantly enhance our ability to understand physical sy…
Randomized Block-Diagonal Preconditioning for Parallel Learning
Celestine Mendler-Dünner, Aurelien Lucchi
We study preconditioned gradient-based optimization methods where the preconditioning matrix has block-diagonal form. Such a structural constraint comes with the advantage that the…