Atinary’s Multi-Fidelity ML Algorithm Now Published
Atinary's latest MFBO study in Nature Computational Science shows how mixing high- and low-fidelity experiments boosts R&D and cuts costs.
We’re proud to share that our latest research on Multi-Fidelity Bayesian Optimization (MFBO) is now published in Nature Computational Science!
How can R&D teams strike the right balance between experimental cost and accuracy?
📘 The paper offers scientists, chemists, and R&D leaders a roadmap to optimize smarter, faster, and more efficiently.
This collaborative work with Profs. Philippe Schwaller (EPFL), Jose Miguel Hernández Lobato (University of Cambridge), Jeremy Luterbacher (EPFL), and their teams explores how combining high- and low-fidelity experiments can accelerate molecular and materials discovery — while reducing optimization costs.
👏 Big congratulations to the authors:
Victor Sabanza Gil, Daniel Pacheco Gutierrez, Jeremy S. Luterbacher, Riccardo Barbano, José M. Hernández-Lobato, Philippe Schwaller, and Loïc Roch
🗞️ For more details:
Read the full publication: https://www.nature.com/articles/s43588-025-00822-9
Accompanying News & Views: https://www.nature.com/articles/s43588-025-00833-6
Related Publications:
