AI2DFT — Auto-Differentiable Density Functional Theory

AI2DFT is an auto-differentiable density functional theory program that enables gradient-based optimization of electronic structure calculations. Key features include:

• Compatibility with pseudo-atomic orbital basis sets
• Norm-conserving pseudopotentials
• Auto-differentiation for variational energy minimization

Associated with the paper: Neural-network density functional theory based on variational energy minimization, Phys. Rev. Lett. 133, 076401 (2024).