Call For Papers for ICML 2012 Workshop on ---------------------------------------------------- *INFERNING*: Interactions between Inference and Learning ---------------------------------------------------- Saturday, June 30th, 2012 Edinburgh, UK http://inferning.cs.umass.edu infern...@iesl.cs.umass.edu
This workshop studies the interactions between algorithms that learn a model, and algorithms that use the resulting model parameters for inference. These interactions are studied from two perspectives. The first perspective studies how the choice of an inference algorithm influences the parameters the model ultimately learns. For example, many parameter estimation algorithms require inference as a subroutine. Consequently, when we are faced with models for which exact inference is expensive, we must use an approximation instead: MCMC sampling, belief propagation, beam-search, etc. On some problems these approximations yield superior models, yet on others, they fail catastrophically. We invite studies that analyze (both empirically and theoretically) the impact of approximate inference on the resulting model. How does approximate inference alter the learning objective? Affect generalization? Influence convergence properties? Further, does the behavior of inference change as learning continues to improve the quality of the model? A second perspective from which we study these interactions is by considering how the learning objective and model parameters can impact both the quality and performance of inference during “test time”. These unconventional approaches to learning combine generalization to unseen data with other desiderata such as fast inference. For example, work in structured cascades learns model for which greedy, efficient inference can be performed at test time while still maintaining accuracy guarantees. Similarly, there has been work that learns operators for efficient search-based inference. There has also been work that incorporates resource constraints on running time and memory into the learning objective. *List of Topics *This workshop brings together practitioners from different fields (information extraction, machine vision, natural language processing, computational biology, etc.) in order to study a unified framework for understanding and formalizing the interactions between learning and inference. The following is a partial list of relevant keywords for the workshop: - learning with approximate inference - cost-aware learning - learning sparse structures (structure learning) - coarse to fine learning and inference - pseudo-likelihood training - contrastive divergence - piecewise training - scoring matching - stochastic approximation - incremental gradient methods *Invited Speakers *- Max Welling, University of California, Irvine (confirmed) - Pedro Domingos, University of Washington (confirmed) - Hal Daume III, University of Maryland, College Park - David Sontag, New York University *Important Dates *Submission Deadline: May 7th, 2012 (11:59pm PST) Author Notification: May 21st, 2012 Workshop: June 30th, 2012 *Author Guidelines *Submissions are encouraged as extended abstracts of ongoing research. The recommended page length is 4 pages (without included references). Additional supplementary content may be included, but may not be considered during the review process. Previously published or currently in submission papers are also encouraged (we will confirm with authors before publishing the papers online). The format of the submissions should follow the ICML 2012 style, available here: http://icml.cc/2012//files/icml2012stylefiles.zip However, since the review process is not double-blind, submissions need not be anonymized and author names may be included. Submission site: https://www.easychair.org/conferences/?conf=inferning2012 *Organizers *Michael Wick <http://cs.umass.edu/~mwick>, University of Massachusetts, Amherst Sameer Singh <http://cs.umass.edu/~sameer/>, University of Massachusetts, Amherst David Weiss <http://www.seas.upenn.edu/~dwe/>, University of Pennsylvania, Philadelphia Andrew McCallum <http://cs.umass.edu/~mccallum>, University of Massachusetts, Amherst
_______________________________________________ uai mailing list uai@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/uai
