Imagine a random walk that outputs a state only when visiting it for the first time. The observed output is therefore a repeat-censored version of the underlying walk, and consists of a permutation of the states or a prefix of it. We call this model initial-visit emitting random walk (INVITE). Prior work has shown that the random walks with such a repeat-censoring mechanism explain well human behavior in memory search tasks, which is of great interest in both the study of human cognition and various clinical applications. However, parameter estimation in INVITE is challenging, because naive likelihood computation by marginalizing over infinitely many hidden random walk trajectories is intractable. In this paper, we propose the first efficient maximum likelihood estimate (MLE) for INVITE by decomposing the censored output into a series of absorbing random walks. We also prove theoretical properties of the MLE including identifiability and consistency. We show that INVITE outperforms several existing methods on real-world human response data from memory search tasks.

We are getting down to the wire--just two and a half weeks until Xconomy's most unique, up close and personal event of the year: our sixth annual Napa Summit: The Xconomy Retreat on Technology, Jobs, and Growth. We have only about 20 spots left open, and a number of those will likely go fast. So request your invitation today to this special conference in the heart of California wine country and join a standout group of executives, innovators, investors, technologists, and entrepreneurs who will be among your fellow attendees. Attendance is limited to no more than 100. To request your invite, visit our event site, or email us at napa17@xconomy.com