aiqbench analysis
This research maps electronic structure calculations onto deep neural network architectures to replace computationally expensive diagonalization with optimized matrix-matrix multiplication kernels. By training machine learning models to predict expansion coefficients, the method achieves an order-of-magnitude speedup on GPUs for finite-temperature density matrix calculations without requiring retraining across different thermodynamic conditions. The approach is particularly relevant for leveraging modern AI hardware to accelerate quantum chemistry simulations on small to moderately sized matrices.
Machine-learned, finite temperature Fermi-operator expansions suitable for GPUs and AI-hardware
arXiv:2605.08523v2 Announce Type: replace Abstract: We present several finite-temperature recursive Fermi-operator expansion schemes based on the second-order spectral projection (SP2) method. Our approach builds on a previous observation that the electronic structure problem, as formulated through a recursive SP2 expansion, can be mapped onto the architecture of a deep neural network. Using this perspective, we generalize SP2 to finite electronic temperatures by constructing machine learning models that determine optimized recursive expansion coefficients. The same approach is also applied to the prediction of the electronic entropy for fractional occupation numbers. The coefficients are trained for a specified chemical potential and electronic temperature and are not available in closed analytical form. However, by employing an appropriate affine rescaling strategy to the Hamiltonian matrix, we eliminate the need to retrain the model for different temperatures and chemical potentials. Our approach avoids explicit diagonalization and relies solely on highly optimized matrix-matrix multiplication kernels. Compared to state-of-the-art diagonalization, we achieve an order-of-magnitude speedup in the single-particle finite-temperature density matrix calculation for small and moderately sized matrices on modern GPUs and dense matrix multiply units.
Abstract:We present several finite-temperature recursive Fermi-operator expansion schemes based on the second-order spectral projection (SP2) method. Our approach builds on a previous observation that the electronic structure problem, as formulated through a recursive SP2 expansion, can be mapped onto the architecture of a deep neural network. Using this perspective, we generalize SP2 to finite electronic temperatures by constructing machine learning models that determine optimized recursive expansion coefficients. The same approach is also applied to the prediction of the electronic entropy for fractional occupation numbers. The coefficients are trained for a specified chemical potential and electronic temperature and are not available in closed analytical form. However, by employing an appropriate affine rescaling strategy to the Hamiltonian matrix, we eliminate the need to retrain the model for different temperatures and chemical potentials. Our approach avoids explicit diagonalization and relies solely on highly optimized matrix-matrix multiplication kernels. Compared to state-of-the-art diagonalization, we achieve an order-of-magnitude speedup in the single-particle finite-temperature density matrix calculation for small and moderately sized matrices on modern GPUs and dense matrix multiply units.
arXiv:2605.08523 [quant-ph]
(or arXiv:2605.08523v2 [quant-ph] for this version)
https://doi.org/10.48550/arXiv.2605.08523 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 263 words
Related coverage
Machine-learned, finite temperature Fermi-operator expansions suitable for GPUs and AI-hardware
arXiv · Sep 23, 2026
News
Quantum Computing Report · Jul 25, 2026
News
Quantum Computing Report · Jun 7, 2026
Operator Score Matching for Learning Quantum Hamiltonians
arXiv · Sep 23, 2026