2025/12/08 by Bedaque, Paulo F., Cigliano, Jacob, Kumar, Hersh +2
#Computational Physics (physics.comp-ph) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Nuclear Theory (nucl-th) #Quantum Gases (cond-mat.quant-gas) #Quantum Physics (quant-ph)
paper · doi:10.48550/arxiv.2512.07800
We investigate a variational Monte Carlo framework for trapped one-dimensional mixture of spin-(1)/(2) fermions using Kolmogorov-Arnold networks (KANs) to construct universal neural-network wavefunction ansätze. The method can, in principle, achieve arbitrary accuracy, limited only by the Monte Carlo sampling and was checked against exact results at sub-percent precision. For attractive interactions, it captures pairing effects, and in the impurity case it agrees with known results. We present a method of systematic transfer learning in the number of network parameters, allowing for efficient training for a target precision. We vastly increase the efficiency of the method by incorporating the short-distance behavior of the wavefunction into the ansätz without biasing the method.