Spectral learning of linear dynamics from generalised-linear observations with 
application to neural population data

Buesing, L; Macke, JH; Sahani, M

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Spectral learning of linear dynamics from generalised-linear observations with application to neural population data

MPS-Authors

There are no MPG-Authors in the publication available

External Resource

https://papers.nips.cc/paper/4836-spectral-learning-of-linear-dynamics-from-generalised-linear-observations-with-application-to-neural-population-data.pdf
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Buesing, L., Macke, J., & Sahani, M. (2013). Spectral learning of linear dynamics from generalised-linear observations with application to neural population data. In P. Bartlett, F. Pereira, L. Bottou, C. Burges, & K. Weinberger (Eds.), Advances in Neural Information Processing Systems 25 (pp. 1691-1699). Red Hook, NY, USA: Curran.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-B54E-3

Abstract

Latent linear dynamical systems with generalised-linear observation models arise in a variety of applications, for example when modelling the spiking activity of populations of neurons. Here, we show how spectral learning methods for linear systems with Gaussian observations (usually called subspace identification in this context) can be extended to estimate the parameters of dynamical system models observed through non-Gaussian noise models. We use this approach to obtain estimates of parameters for a dynamical model of neural population data, where the observed spike-counts are Poisson-distributed with log-rates determined by the latent dynamical process, possibly driven by external inputs. We show that the extended system identification algorithm is consistent and accurately recovers the correct parameters on large simulated data sets with much smaller computational cost than approximate expectation-maximisation (EM) due to the non-iterative nature of subspace identification. Even on smaller data sets, it provides an effective initialization for EM, leading to more robust performance and faster convergence. These benefits are shown to extend to real neural data.