State Space LSTM Models with Particle MCMC Inference
Not on the map. Why?
Abstract (arXiv)
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) models that generalizes the earlier work citezaheer2017latent of combining topic models with LSTM. However, unlike citezaheer2017latent, 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.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 2; 2023: 3.
11 papers.
- 2023Resurrecting Recurrent Neural Networks for Long Sequencescited by 408
- 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamicscited by 132
- 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluationcited by 42
- 2022Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systemscited by 36
- 2021CAMul: Calibrated and Accurate Multi-view Time-Series Forecastingcited by 17
- 2021Unsupervised Learned Kalman Filteringcited by 17
- 2023Bifurcations and loss jumps in RNN trainingcited by 17
- 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
- 2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learningcited by 13
- 2023The Bayesian Context Trees State Space Model for time series modelling and forecastingcited by 2
- 2021Switching Recurrent Kalman Networkscited by 0
- 2023Bifurcations and loss jumps in RNN training26 Oct 2023
- 2023The Bayesian Context Trees State Space Model for time series modelling and forecasting2 Aug 2023
- 2023Resurrecting Recurrent Neural Networks for Long Sequences11 Mar 2023
- 2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning17 Oct 2022
- 2022Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems6 Jul 2022
- 2021Switching Recurrent Kalman Networks16 Nov 2021
- 2021Unsupervised Learned Kalman Filtering18 Oct 2021
- 2021CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting15 Sep 2021
- 2021KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics21 Jul 2021
- 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecasting10 Jun 2021
- 2021Causal Inference for Time series Analysis: Problems, Methods and Evaluation11 Feb 2021