Linear Additive Markov Processes
This provides a more efficient alternative to higher-order Markov processes for sequential modeling tasks, though it appears incremental in scope.
The authors tackled the problem of modeling transitions influenced by distant history in sequential processes by introducing LAMP, a Linear Additive Markov Process that retains efficient parametrization and learning from data, showing it outperforms first-order Markov processes and competes with LSTMs with minimal parameter increase.
We introduce LAMP: the Linear Additive Markov Process. Transitions in LAMP may be influenced by states visited in the distant history of the process, but unlike higher-order Markov processes, LAMP retains an efficient parametrization. LAMP also allows the specific dependence on history to be learned efficiently from data. We characterize some theoretical properties of LAMP, including its steady-state and mixing time. We then give an algorithm based on alternating minimization to learn LAMP models from data. Finally, we perform a series of real-world experiments to show that LAMP is more powerful than first-order Markov processes, and even holds its own against deep sequential models (LSTMs) with a negligible increase in parameter complexity.