45 citations · 57 across the 6 of their papers we have counts for
11 papers
Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces
Ziyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti +3
Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, howev…
Generating stable molecules using imitation and reinforcement learning
Søren Ager Meldgaard, Jonas Köhler, Henrik Lund Mortensen +3
Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted. However, these met…
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…
Learning Generative Models of Textured 3D Meshes from Real-World Images
Dario Pavllo, Jonas Kohler, Thomas Hofmann +1
Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections. These models natively disentangle p…
Two-Level K-FAC Preconditioning for Deep Learning
Nikolaos Tselepidis, Jonas Kohler, Antonio Orvieto
In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent. In particular,…
Training Invertible Linear Layers through Rank-One Perturbations
Andreas Krämer, Jonas Köhler, Frank Noé
Many types of neural network layers rely on matrix properties such as invertibility or orthogonality. Retaining such properties during optimization with gradient-based stochastic o…