Connectionists: CFP: ICML 2013 Workshop on Inferning: Interactions between Inference and Learning

Ruslan Salakhutdinov rsalakhu at cs.toronto.edu
Tue Feb 26 23:44:35 EST 2013




Call for Papers

ICML 2013 Workshop on Inferning: Interactions between Inference and Learning

http://inferning.cs.umass.edu inferning2013 at gmail.com

Important Dates:
Submission Deadline: Mar 30th, 2013 (11:59pm PST)
Author Notification: April 21st, 2013
Workshop: June 20-21, 2013, Atlanta, GA


There are strong interactions between learning algorithms which estimate the 
parameters of a model from data, and inference algorithms which use a model to 
make predictions about data. Understanding the intricacies of these 
interactions is crucial for advancing the state-of-the-art on real-world tasks 
in natural language processing, computer vision, computation biology, etc. Yet, 
many facets of these interactions remain unknown. In this workshop, we study 
the interactions between inference and learning using two reciprocating 
perspectives.

Perspective one: how does inference affect learning? The first perspective 
studies the influence of the choice of inference technique during learning on 
the resulting model. When faced with models for which exact inference is 
intractable, efficient approximate inference techniques may be used, such as 
MCMC sampling, stochastic approximation, belief propagation, beam-search, dual 
decomposition, etc. The workshop will focus on work that evaluates the impact 
of the approximations on the resulting parameters, in terms of both the 
generalization of the model, the effect it has on the objective functions, and 
the convergence properties. We will also study approaches that attempt to 
correct for the approximations in inference by modifying the objective and/or 
the learning algorithm (for example, contrastive divergence for deep 
architectures), and approaches that minimize the dependence on the inference 
algorithms by exploring inference-free methods (e.g., piece-wise training, 
pseudo-max and decomposed learning).

Perspective two: how does learning affect inference? Traditionally, the goal of 
learning has been to find a model for which prediction (i.e., inference) 
accuracy is as high as possible. However, an increasing emphasis on modeling 
complexity has shifted the goal of learning: find models for which prediction 
(i.e., inference) is as efficient as possible. Thus, there has been recent 
interest in more unconventional approaches to learning that combine 
generalization accuracy with other desiderata such as faster inference. Some 
examples of this kind are: learning classifiers for greedy inference (e.g., 
Searn, Dagger); structured cascade models that learn a cost function to perform 
multiple runs of inference from coarse to fine level of abstraction by 
trading-off accuracy and efficiency at each level; learning cost function to 
search in the space of complete outputs (e.g., SampleRank, search in Limited 
Discrepancy Search space); learning structures that exhibit efficient exact 
inference etc. Similarly, there has been work that learns operators for 
efficient search-based inference, approaches that trade-off speed and accuracy 
by incorporating resource constraints such as run-time and memory into the 
learning objective.


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
* pseudo-likelihood, composite likelihood training
* contrastive divergence
* piece-wise and decomposed training
* decomposed learning
* coarse to fine learning and inference
* score matching
* stochastic approximation
* incremental gradient methods
* adaptive proposal distributions
* learning for anytime inference
* learning approaches that trade-off speed and accuracy
* learning to speed up inference
* learning structures that exhibit efficient exact inference
* lifted inference for first-order models
* more ...

New benchmark problems: This line of research can hugely benefit from new 
challenge problems from various fields (e.g., computer vision, natural language 
processing, speech, computational biology, computational sustainability, etc.). 
Therefore, we especially request relevant papers describing such problems, main 
challenges, evaluations and public data sets.


Invited Speakers:

Dan Roth, University of Illinois, Urbana-Champaign
Rina Dechter, University of California, Irvine
Ben Taskar, University of Washington
Hal Daume, University of Maryland, College Park
Alan Fern, Oregon State University


Important Dates:

Submission Deadline: Mar 30th, 2013 (11:59pm PST)
Author Notification: April 21st, 2013
Workshop: June 20-21, 2013


Author Guidelines:

Submissions are encouraged as extended abstracts of ongoing research. The 
recommended page length is 4-6 pages. 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 2013 style, available 
here: http://icml.cc/2013/wp-content/uploads/2012/12/icml2013stylefiles.tar.gz 
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=inferning2013


Organizers:

Janardhan Rao (Jana) Doppa, Oregon State University
Pawan Kumar, Ecole Centrale Paris
Michael Wick, University of Massachusetts, Amherst
Sameer Singh, University of Massachusetts, Amherst
Ruslan Salakhutdinov, University of Toronto


More information about the Connectionists mailing list