DISCML 2014 - 6th Workshop on Discrete Optimization in Machine Learning

DISCML -- 6th Workshop on Discrete Optimization in Machine Learning
at NIPS 2014 (Montreal)
Dec 13, 2014
www.discml.cc
Submission deadline: Oct 23, 2014
===
Discrete optimization problems and combinatorial structures are becoming
increasingly important in machine learning. They arise for discrete
labels with complex dependencies, structured estimators, learning with
graphs, partitions, permutations, or when selecting informative subsets
of data or features.
What are efficient algorithms for handling such problems? Can we robustly
solve them in the presence of noise? What about streaming or distributed
settings? Which models are computationally tractable and rich enough for
applications? What theoretical worst-case bounds can we show?
What explains good performance in practice?
Such questions are the theme of the DISCML workshop. It aims to bring
together theorists and practitioners to explore new applications, models
and algorithms, and mathematical properties and concepts that can help
learning with complex interactions and discrete structures.
We invite high-quality submissions that present recent results related
to discrete and combinatorial problems in machine learning, and submissions
that discuss open problems or controversial questions and observations,
e.g., missing theory to explain why algorithms work well in certain
instances but not in general, or illuminating worst case examples.
We also welcome the description of well-tested software and benchmarks.
Areas of interest include, but are not restricted to:
* discrete optimization for machine learning
* graph algorithms
* relaxations
* learning of discrete structures
* new models (e.g. diversity priors, regularization, discrete probabilistic models)
* algorithms for large data (streaming, sketching, distributed)
* online learning
* new applications
Submissions:
Please send submissions in NIPS 2014 format (length max. 6 pages, non-anonymous) to
submitdiscml.cc
submission deadline: October 23, 2014.
Organizers:
Andreas Krause (ETH Zurich, Switzerland),
Jeff A. Bilmes (University of Washington, Seattle),
Stefanie Jegelka (UC Berkeley)