• Corpus ID: 18383512

BLACK BOX VARIATIONAL INFERENCE FOR STATE SPACE MODELS

@article{Archer2016BLACKBV,
  title={BLACK BOX VARIATIONAL INFERENCE FOR STATE SPACE MODELS},
  author={Evan Archer and Il Memming Park and Lars Buesing and John P. Cunningham and Liam Paninski},
  journal={arXiv: Machine Learning},
  year={2016}
}
Latent variable time-series models are among the most heavily used tools from machine learning and applied statistics. These models have the advantage of learning latent structure both from noisy observations and from the temporal ordering in the data, where it is assumed that meaningful correlation structure exists across time. A few highly-structured models, such as the linear dynamical system with linear-Gaussian observations, have closed-form inference procedures (e.g. the Kalman Filter… 

Figures from this paper

Self-Supervised Hybrid Inference in State-Space Models
TLDR
Despite the model’s simplicity, it obtains competitive results on the chaotic Lorenz system compared to a fully supervised approach and outperform a method based on variational inference.
A Novel Variational Family for Hidden Nonlinear Markov Models
TLDR
A novel variational inference framework for the explicit modeling of time series, Variational Inference for Nonlinear Dynamics (VIND), is proposed that is able to uncover nonlinear observation and transition functions from sequential data.
Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
TLDR
This work proposes a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations and uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions.
Structured Inference Networks for Nonlinear State Space Models
TLDR
A unified algorithm is introduced to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks.
The neural moving average model for scalable variational inference of state space models
TLDR
This work proposes an extension to state space models of time series data based on a novel generative model for latent temporal states: the neural moving average model, which permits a subsequence to be sampled without drawing from the entire distribution, enabling training iterations to use mini-batches of the time series at low computational cost.
Structured Variational Inference in Unstable Gaussian Process State Space Models
TLDR
CBF-SSM is proposed a scalable model that employs a structured variational approximation to maintain temporal correlations in Gaussian processes and can be combined with physical models in the form of ordinary differential equations to learn a reliable model of a physical flying robotic vehicle.
Structured Variational Inference in Partially Observable UnstableGaussian Process State Space Models
TLDR
A new variational inference algorithm for learning in Gaussian Process State-Space Models (GPSSMs) with main algorithmic contribution a novel approximate posterior that can be calculated using a single forward and backward pass along the training trajec-tories.
Scalable approximate inference for state space models with normalising flows
TLDR
A novel generative model is introduced as a variational approximation, a local inverse autoregressive flow that allows a subsequence to be sampled without sampling the entire distribution, so that one can perform training iterations using short portions of the time series at low computational cost.
Structured Inference for Recurrent Hidden Semi-markov Model
TLDR
A structured and stochastic sequential neural network (SSNN), which composes with a generative network and an inference network that aims to not only capture the long-term dependencies but also model the uncertainty of the segmentation labels via semi-Markov models.
Stochastic Gradient MCMC for State Space Models
TLDR
This work proposes stochastic gradient estimators that control this bias by performing additional computation in a `buffer' to reduce breaking dependencies and develops novel SGMCMC samplers for discrete, continuous and mixed-type SSMs with analytic message passing.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Deep Kalman Filters
TLDR
A unified algorithm is introduced to efficiently learn a broad spectrum of Kalman filters and investigates the efficacy of temporal generative models for counterfactual inference, and introduces the "Healing MNIST" dataset where long-term structure, noise and actions are applied to sequences of digits.
A new look at state-space models for neural data
TLDR
Direct optimization methods that avoid approximations but that nonetheless retain the computational efficiency of the approximate methods are reviewed, including Markov chain Monte Carlo methods for neural decoding and efficient estimation of spatially-varying firing rates.
Auto-Encoding Variational Bayes
TLDR
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Fast Dual Variational Inference for Non-Conjugate Latent Gaussian Models
TLDR
This work derives a novel dual variational inference approach that exploits the convexity property of the VG approximations and obtains an algorithm that solves a convex optimization problem, reduces the number of variational parameters, and converge much faster than previous methods.
Robust learning of low-dimensional dynamics from large neural ensembles
TLDR
This work shows on model data that the parameters of latent linear dynamical systems can be recovered, and that even if the dynamics are not stationary the authors can still recover the true latent subspace, and demonstrates an extension of nuclear norm minimization that can separate sparse local connections from global latent dynamics.
Spectral learning of linear dynamics from generalised-linear observations with application to neural population data
TLDR
The extended subspace identification algorithm is consistent and accurately recovers the correct parameters on large simulated data sets with a single calculation, avoiding the costly iterative computation of approximate expectation-maximisation (EM).
Stochastic Backpropagation and Approximate Inference in Deep Generative Models
We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and
Variational Inference with Normalizing Flows
TLDR
It is demonstrated that the theoretical advantages of having posteriors that better match the true posterior, combined with the scalability of amortized variational approaches, provides a clear improvement in performance and applicability of variational inference.
Stochastic variational inference
TLDR
Stochastic variational inference lets us apply complex Bayesian models to massive data sets, and it is shown that the Bayesian nonparametric topic model outperforms its parametric counterpart.
An Introduction to Variational Methods for Graphical Models
TLDR
This paper presents a tutorial introduction to the use of variational methods for inference and learning in graphical models (Bayesian networks and Markov random fields), and describes a general framework for generating variational transformations based on convex duality.
...
1
2
3
4
...