Amortized Neural Filtering for Calibrating Posteriors in Statistical Arbitrage

The paper proposes a Neural Filter Estimator (NFE), trained on simulated paths of mean-reverting processes, that outputs the posterior distribution of the implied state for each spread in the cross-section in a single forward pass, incorporating estimation uncertainty into trading decisions. On simulated paths with known ground truth, the method achieves accuracy comparable to other practical estimators, with its advantage lying in correctly characterizing its own uncertainty.