Search Results for author: Philipp Dahlinger

Found 4 papers, 3 papers with code

Latent Task-Specific Graph Network Simulators

1 code implementation9 Nov 2023 Philipp Dahlinger, Niklas Freymuth, Michael Volpp, Tai Hoang, Gerhard Neumann

Movement primitives further allow us to accommodate various types of context data, as demonstrated through the utilization of point clouds during inference.

Meta-Learning Trajectory Prediction

Information-Theoretic Trust Regions for Stochastic Gradient-Based Optimization

1 code implementation31 Oct 2023 Philipp Dahlinger, Philipp Becker, Maximilian Hüttenrauch, Gerhard Neumann

Before each update, it solves the trust region problem for an optimal step size, resulting in a more stable and faster optimization process.

A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models

1 code implementation23 Sep 2022 Oleg Arenz, Philipp Dahlinger, Zihan Ye, Michael Volpp, Gerhard Neumann

The two currently most effective methods for GMM-based variational inference, VIPS and iBayes-GMM, both employ independent natural gradient updates for the individual components and their weights.

Variational Inference

A First-Order Method for Estimating Natural Gradients for Variational Inference with Gaussians and Gaussian Mixture Models

no code implementations29 Sep 2021 Oleg Arenz, Zihan Ye, Philipp Dahlinger, Gerhard Neumann

Effective approaches for Gaussian variational inference are MORE, VOGN, and VON, which are zero-order, first-order, and second-order, respectively.

Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.