State Space LSTM Models with Particle MCMC Inference

Xun Zheng, Manzil Zaheer, Amr Ahmed, Yuan Wang, Eric P. Xing, Alex Smola

Abstract: Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL), which generalizes the earlier work \cite{zaheer2017latent} of combining topic models with LSTM. However, unlike \cite{zaheer2017latent}, we do not make any factorization assumptions in our inference algorithm. We present an efficient sampler based on sequential Monte Carlo (SMC) method that draws from the joint posterior directly. Experimental results confirms the superiority and stability of this SMC inference algorithm on a variety of domains.

TL;DR: We present State Space LSTM models, a combination of state space models and LSTMs, and propose an inference algorithm based on sequential Monte Carlo.

Keywords: recurrent neural networks, state space models, sequential Monte Carlo