QuanVI: Score-based Variational Inference via Quantum Maximally Mixed States
Score-based variational inference (VI) provides an alternative to Kullback--Leibler (KL)-based VI by minimizing the Fisher divergence between the variational distribution and the target. A prior score-VI approach formulates this optimization as an eigenvalue problem, with the variational distribution constructed from l...
Yu Cong, Ze-Rui Tao, Chao Li et al.
· 1 citation