Florian Dietrich
banner
floriandietrix.bsky.social
Florian Dietrich
@floriandietrix.bsky.social
Postdoc @italk.bsky.social

(almost) serious scientist
Method Development | Computational Chemistry | Machine Learning | Enhanced Sampling
New Paper out with Matteo Salvalaglio:
doi.org/10.1063/5.02...

In this letter we explore the theoretical implications of using machine learned collective variables and derive best practices to ensure reproducibility and combat the most common practical challenges when working with MLCVs.
On the reproducibility of free energy surfaces in machine-learned collective variable spaces
As Machine-Learned Collective Variables (MLCVs) are becoming increasingly relevant in the molecular simulation literature, we discuss the necessary conditions t
doi.org
October 18, 2025 at 2:07 PM
Reposted by Florian Dietrich
On the Reproducibility of Free Energy Surfaces in Machine-Learned Collective Variable Spaces

Authors: Florian M. Dietrich, Matteo Salvalaglio
DOI: 10.26434/chemrxiv-2025-g6q8f
March 10, 2025 at 11:47 AM