Anima Anandkumar

Neural operators can now learn directly from noisy, low-cost Monte Carlo estimates, achieving $10^4$-$10^5\times$ speedups for particle transport problems without sacrificing accuracy.

This work introduces PosteriorBench, a benchmark for evaluating the distributional accuracy of generative inverse solvers, and reveals substantial distribution-matching gaps across current solvers, while showing that neural operators improve resolution robustness, and guidance weights and generation noise are key to posterior-variance calibration.