Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation

ArXi:2601.22367v2 Announce Type: replace-cross Generalized Bayesian Inference (GBI) tempers a loss with a temperature $\beta > 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $\beta$ value. We give the first fully amortized variational approximation for the tempered posterior family by