LSKL 2015 - 2015 workshop "Large-scale Kernel Learning: challenges and new opportunities"

The ICML 2015 workshop "Large-scale Kernel Learning: challenges and new opportunities" invites paper submissions that will be presented as spotlights or posters. Topics of interest include (but are not limited to):
- Foundational algorithmic techniques for large-scale kernel learning: matrix factorization, randomization and approximation, variational inference and sampling, inducing variables, random Fourier features, unifying frameworks
- Interface between kernel methods and deep learning architectures
- Tradeoffs between statistical and computational efficiency in kernel methods
- Kernel methods and Gaussian processes for Big Data
- Kernel methods and Gaussian processes on GPUs and other hardware and software systems
- Stochastic gradient techniques with kernel methods
- Large-scale multiple kernel learning
- Large-scale representation learning with kernels
- Large-scale kernel methods for complex data types beyond perceptual data
Both theoretical contributions and empirical studies will be considered. Submissions should be written as extended abstracts, no longer than 5 pages (excluding references) in the camera-ready format using the ICML style. Relevant work previously presented in other conferences will be allowed, though authors should note this in their submission. All submissions must be in PDF format and should be sent by email to lskl.workshop.icml2015-AT-gmail.com. Authors should note that the workshop presentation (slides, posters, etc) will not be considered as a part of formal proceedings.
Please check the workshop website (https://sites.google.com/site/largescalekernelwsic... ) for updated info. We have confirmed a list of stellar speakers: Francis Bach (ENS), Zaid Harchaoui (INRIA), Marius Kloft (Humbold U of Berlin), Neil Lawrence (Sheffeld), Ruslan Salakhutdinov (Toronto) and more are to be confirmed.
Deadline for Submissions: Friday, May 1st, 2015, 23:00 UTC.
Notifications of Acceptance : May 10th, 2015.