Soft GRAND under Channel Switching and Drift

Abstract

Under channel switching or drift, the posterior used to order soft GRAND queries can differ from the matched correction posterior, which can increase rank and finite-budget decoding error. We bound log query rank by matched posterior self-information plus positive log-posterior mismatch; exact random-subset collision probabilities yield GRANDAB error bounds. For switching among memoryless channels with capacity-achieving uniform input, a state-path mixture yields vanishing error uniformly over admissible paths below the minimum constituent capacity when log path-class size is sublinear. For drift, pilot refresh bounds mismatch and yields the continuous minimizer of a tracking upper bound. Generalized-Gaussian BPSK experiments evaluate both.