Skip to Main content Skip to Navigation
Conference papers

Non-negative Spectral Learning for Linear Sequential Systems

Abstract : Method of moments (MoM) has recently become an appealing alternative to standard iterative approaches like Expectation Maximization (EM) to learn latent variable models. In addition, MoM-based algorithms come with global convergence guarantees in the form of finite sample bounds. However, given enough computation time, by using restarts and heuristics to avoid local optima, iterative approaches often achieve better performance. We believe that this performance gap is in part due to the fact that MoM-based algorithms can output negative probabilities. By constraining the search space, we propose a non-negative spectral algorithm (NNSpectral) avoiding computing negative probabilities by design. NNSpectral is compared to other MoM-based algorithms and EM on synthetic problems of the PAutomaC challenge. Not only, NNSpectral outperforms other MoM-based algorithms, but also, achieves very competitive results in comparison to EM.
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Olivier Pietquin Connect in order to contact the contributor
Submitted on : Friday, November 6, 2015 - 6:26:40 PM
Last modification on : Saturday, December 18, 2021 - 3:05:17 AM
Long-term archiving on: : Monday, February 8, 2016 - 1:02:10 PM


Files produced by the author(s)


  • HAL Id : hal-01225838, version 1


Hadrien Glaude, Cyrille Enderli, Olivier Pietquin. Non-negative Spectral Learning for Linear Sequential Systems. 22nd International Conference on Neural Information Processing (ICONIP2015), Nov 2015, Istanbul, Turkey. ⟨hal-01225838⟩



Les métriques sont temporairement indisponibles