Reduced space hidden Markov model

1 Abstract 1.1 Motivation Complete forward-backward (Baum-Welch) hidden Markov model training cannot take advantage of the linear space, divide-and-conquer sequence alignment algorithms because of the examination of all possible paths rather than the single best path. This paper discusses the implementation and performance of checkpoint-based reduced space sequence alignment in the SAM Hidden Markov mod-eling package. Implementation of the checkpoint algorithm reduced memory usage from O(mn) to O(m p n) with only a 10% slowdown for small m and n and vast speedup for the larger values, such as m = n = 2000, that cause excessive paging on a 96 MByte workstation. The results are applicable to other types of dynamic programming.