“I think I can safely say that nobody understands quantum mechanics.” —Richard Feynman
“But we can still make it useful with Math and Programming.” —Valerii Chuiko
Tackling Quantum Complexity through Machine Learning, Optimal Transport, and Open Science
I am a third-year PhD student working to tackle one of the fundamental challenges in modern quantum chemistry: the curse of dimensionality.
The computational cost of accurately describing quantum systems grows exponentially with system size, creating a barrier to discovering new drugs, antibiotics, and materials.
To address this, I approach the problem from three complementary directions: Deep Learning methods for Quantum Chemistry, Optimal Transport applications to Reduced Density Matrix Functional Theory, and Scientific Software Development.
🧠 Deep Learning
Developing Deep Learning models to predict quantum system properties, under the supervision of Prof. Paul W. Ayers.
We are focusing on learning the electronic structure by developing molecular descriptors and suitable NN architectures.
Latest results: a novel descriptor for energy prediction — read the preprint.
🔀 Optimal Transport
Exploring the connection between Reduced Density Matrix Functional Theory and Quantum Optimal Transport, with Prof. Augusto Gerolin.
This research has garnered significant attention from the mathematics community, and we are currently developing extensions as part of a collaborative visit to UCLA. Preprints and code will be available soon.
🛠️ Open-Source Software
Building accessible, open-source tools for quantum chemists and physicists as part of the QC-Devs consortium in collaboration with Farnaz Heidar-Zadeh.
Leading contributions to ModelHamiltonian, PyCI, Selector, and AtomDB.
Additionally, I mentor the next generation of programmers through my involvement with Google Summer of Code.