WSL 2013 - Workshop on Spectral Learning

Many problems in machine learning involve collecting high-dimensional multivariate observations or sequences of observations, and then fitting a compact model which explains these observations. Recently, linear algebra techniques have given a fundamentally different perspective on how to fit and perform inference in these models. Exploiting the underlying spectral properties of the model parameters has led to fast, provably consistent methods for parameter learning that stand in contrast to previous approaches, such as Expectation Maximization, which suffer from slow convergence and issues related to local optima.
In the past several years, these spectral learning algorithms have become increasingly popular. They have been applied to learn the structure and parameters of many models including predictive state representations, finite state transducers, hidden Markov models, latent trees, latent junction trees, probabilistic context free grammars, and mixture/admixture models. Spectral learning algorithms have also been applied to a wide range of application domains including system identification, video modeling, speech modeling, robotics, and natural language processing.
The focus of this workshop will be on spectral learning algorithms, broadly construed as any method that fits a model by way of a spectral decomposition of moments of (features of) observations. We would like the workshop to be as inclusive as possible and encourage paper submissions and participation from a wide range of research related to this focus. This includes (but is not limited to):
Linear-algebraic methods for estimation and inference in probabilistic models and weighted automata/operator models
Spectral approaches to dimension reduction (e.g., with applications in estimating mixture models)
Method-of-moment estimation via higher-order tensor decompositions
Spectral graph theory and applications in clustering and learning on manifolds
Domain-specific aspects of using spectral approaches in applications
Submitted papers should be in the ICML 2013 format with a maximum of 4 pages (not including references). Please e-mail your submission to spectralicml2013-AT-gmail.com with the subject line "Submission to Spectral Learning Workshop". Contributions will be considered for both short talks and poster presentations.
Concurrent submissions to the workshop and the main conference (or other conferences) are permitted.
Important dates:
Submission deadline: April 6, 2013
Notification of acceptance: April 20, 2013 (tentative)
Workshop: June 20 or 21, 2013
Organizers:
Byron Boots (University of Washington)
Daniel Hsu (Microsoft Research New England)
Borja Balle (Universitat Politècnica de Catalunya)
Ankur Parikh (Carnegie Mellon University)