Scholar
Georgios Arvanitidis
Google Scholar ID: sFtJbSUAAAAJ
Cognitive Systems, DTU Compute, Technical University of Denmark
Citations & Impact
Citations
682
H-index
12
i10-index
12
Publications
20
Co-authors
8
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers in areas such as differential geometry in machine learning, representation learning, and generative models. Some of the publications include:
- - "Staying on the Manifold: Geometry-Aware Noise Injection" (2025)
- - "Connecting Neural Models Latent Geometries with Relative Geodesic Representations" (2025)
- - "Learning geometry and topology via multi-chart flows" (2025)
- - "Geodesic Slice Sampler for Multimodal Distributions with Strong Curvature" (2025)
- - "Monge SAM: Robust Reparameterization-Invariant Sharpness-Aware Minimization Based on Loss Geometry" (2025)
- - "Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions" (2025)
- - "Counterfactual Explanations via Riemannian Latent Space Traversal" (2024)
- - "Neural Contractive Dynamical Systems" (2024)
- - "On the curvature of the loss landscape" (2023)
- - "Riemannian Laplace approximations for Bayesian neural networks" (2023)
- - "On Data Manifolds Entailed by Structural Causal Models" (2023)
- - "Reactive Motion Generation on Learned Riemannian Manifolds" (2023)
- - "A prior-based approximate latent Riemannian metric" (2022)
- - "Pulling back information geometry" (year not specified)
Research Experience
- Currently an associate professor at the Section for Cognitive Systems (CogSys) at the Technical University of Denmark (DTU). Previously a PostDoc at the Max Planck Institute for Intelligent Systems, working with Bernhard Schölkopf. Visited Philipp Hennig's Probabilistic Numerics group during his PhD.
Education
- PhD from the Section for Cognitive Systems (CogSys) at the Technical University of Denmark (DTU), supervised by Søren Hauberg; Master's degree in Computer Science from Saarland University, supported by the Max Planck Institute for Informatics; Bachelor's degree from the Department of Informatics at Aristotle University of Thessaloniki.
Background
- Research interests include differential geometry in machine learning, representation learning, generative models, deep learning theory, and approximate Bayesian inference.
Miscellany
- Contact: name@dtu.dk (replace 'name' with 'gear'), office located at Building 321, room 224.
