A proximal gradient algorithm for composite log-concave sampling
The paper proposes a proximal gradient algorithm to sample from complex distributions where density is proportional to exp(-f-g). It uses gradient evaluations for f and a restricted Gaussian oracle (RGO) for g. The method achieves $\epsilon$ accuracy in total variation distance using $\widetilde{\mathcal{O}}(\kappa\sqrt d \log^4(1/\epsilon))$ calls, matching prior state-of-the-art complexity when $g=0$, and improving the dimensional dependence to $\sqrt d$.