User profiles for Philipp Dahlinger
Philipp DahlingerKarlsruhe Institute of Technology (KIT) Verified email at kit.edu Cited by 44 |
A unified perspective on natural gradient variational inference with gaussian mixture models
Variational inference with Gaussian mixture models (GMMs) enables learning of highly
tractable yet multi-modal approximations of intractable target distributions with up to a few …
tractable yet multi-modal approximations of intractable target distributions with up to a few …
Swarm reinforcement learning for adaptive mesh refinement
The Finite Element Method, an important technique in engineering, is aided by Adaptive Mesh
Refinement (AMR), which dynamically refines mesh regions to allow for a favorable trade-…
Refinement (AMR), which dynamically refines mesh regions to allow for a favorable trade-…
Human-machine symbiosis: A multivariate perspective for physically coupled human-machine systems
The notion of symbiosis has been increasingly mentioned in research on physically coupled
human-machine systems. Yet, a uniform specification on which aspects constitute human-…
human-machine systems. Yet, a uniform specification on which aspects constitute human-…
Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization
Stochastic gradient-based optimization is crucial to optimize neural networks. While popular
approaches heuristically adapt the step size and direction by rescaling gradients, a more …
approaches heuristically adapt the step size and direction by rescaling gradients, a more …
Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards
Simulating physical systems is essential in engineering, but analytical solutions are limited
to straightforward problems. Consequently, numerical methods like the Finite Element …
to straightforward problems. Consequently, numerical methods like the Finite Element …
Accurate bayesian meta-learning by accurate task posterior inference
Bayesian meta-learning (BML) enables fitting expressive generative models to small datasets
by incorporating inductive priors learned from a set of related tasks. The Neural Process (…
by incorporating inductive priors learned from a set of related tasks. The Neural Process (…
Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations
Many engineering systems require accurate simulations of complex physical systems. Yet,
analytical solutions are only available for simple problems, necessitating numerical …
analytical solutions are only available for simple problems, necessitating numerical …
A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models
Variational inference with full-covariance Gaussian approximations is an important line of
research, as such Gaussian variational approximations (GVAs) allow for tractable approximate …
research, as such Gaussian variational approximations (GVAs) allow for tractable approximate …
Latent Task-Specific Graph Network Simulators
Simulating dynamic physical interactions is a critical challenge across multiple scientific
domains, with applications ranging from robotics to material science. For mesh-based …
domains, with applications ranging from robotics to material science. For mesh-based …
Preventing traffic accidents with in-vehicle decision support systems-The impact of accident hotspot warnings on driver behaviour
Despite continuous investment in road and vehicle safety, as well as improvements in
technology standards, the total amount of road traffic accidents has been increasing over the last …
technology standards, the total amount of road traffic accidents has been increasing over the last …