Adrian Hill
Adrian Hill
Doctoral Researcher
Adrian Hill is a PhD student at the TU Berlin Machine Learning Group. He received his M.Sc. in Engineering Science at TU Berlin with a focus on numerics and control theory. His research interests lie at the intersection of Machine Learning and dynamical systems.
- Neural ODEs
- Inverse Problems
- Molecular dynamics
- Automatic Differentiation
- Explainable AI
Adrian Hill, Guillaume Dalle
asdex: Automatic Sparse Differentiation in JAX
Marcel F. Langer, Adrian Hill, Michele Ceriotti
Truncated automatic sparse differentiation for machine learning interatomic potentials
Adrian Hill, Neal McKee, Johannes Maeß, Stefan Bluecher, Klaus Robert Muller
Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations
Guillaume Dalle, Adrian Hill
A Common Interface for Automatic Differentiation
Jan Swierczek-Jereczek, Adrian Hill, Alexander Robinson, Jorge Alvarez-Solas, Marisa Montoya
A reduced-order representation of the West Antarctic Ice Sheet
Open-Source Award for DifferentiationInterface.jl
DifferentiationInterface.jl, co-developed by BIFOLD researcher Adrian Hill, wins one of France’s Open Science Awards for making cutting-edge modeling and optimization more flexible, efficient, and open.