How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL
It is proved that an unbounded gap between the update maps can coexist with vanishing predictive KL for every fixed finite $K\ge2$ in a stationary symmetric Gaussian HMM, and isolates two missing links between internal update gaps and predictive cost.
Qi-Fu Wen, Shuai Liu, Zihan Zhou et al.
· 0 citations