Wiener–Kolmogorov Filtering

The linear filtering theory that yields the minimum mean‑square error (MMSE) linear estimator for stationary stochastic processes. In the frequency domain it produces a (generally noncausal) transfer function that minimizes output MSE given known power spectral densities; Kolmogorov's contribution further provides factorization methods to obtain causal (one‑sided) predictors when required.