arXiv:2606.28911v1 Announce Type: new Abstract: Machine-learned (ML) operator models can be trained to predict density functional theory (DFT) Hamiltonian/density matrices at significantly reduced computational cost, thus extending electronic-structure calculations to previously unfeasible scales. Here, we introduce MALOQ (Massively Accelerated Learning of Operators for Quantum Transport), an application built to train on and predict electronic-structure matrices for systems made of few to 100k atoms, described by large basis sets, and covering a wide range of atomic elements. Based on a state
The proliferation of advanced AI models and increasing computational demands for materials science and quantum computing necessitate more efficient simulation techniques.
This development allows for significantly faster and larger-scale electronic-structure calculations, which are foundational for materials discovery, drug design, and quantum technology development.
Machine learning can now accelerate quantum transport simulations by several orders of magnitude, making previously unfeasible large-scale atomic system analyses possible.
- · Materials science researchers
- · Pharmaceutical industry
- · Compute infrastructure providers
- · AI hardware manufacturers
- · Traditional high-performance computing methods for DFT
- · Research groups reliant solely on classical DFT approaches
Accelerated discovery of new materials with superior properties for various industrial applications.
Reduced R&D cycles for products reliant on novel materials, leading to faster innovation in sectors like energy, electronics, and aerospace.
Potential for an 'AI for Science' arms race, where nations compete in applying advanced machine learning to fundamental scientific problems to gain an economic and technological edge.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG