Call for Participation

Call For Participation

We invite participation in the Workshop on "Advances in Active Learning - Bridging Theory and Practice", to be held as a part of the ICML 2015 conference in Lille, France (July 6-11, 2015). 

Important Dates

Deadline for submissions : May 1, 2015 (via email, details below)
Notification of acceptance : May 10, 2015
Workshop date : July 10, 2015 (Friday, first day of workshops)

Overview

Active learning has been a topic of significant research over the past several decades with much attention devoted to both theoretical and practical considerations. A variety of algorithms and sampling paradigms have been proposed and studied, but roughly speaking, this line of research focuses on how to make feedback driven decisions about data collection, and how to leverage this power for efficient learning. Research in this area stems from a range of communities including signal processing, machine learning, statistics, and information theory, including both theoreticians and practitioners. One aim of this workshop is to bring this diverse collection of researchers together. 

Despite attention from both theoreticians and practitioners, there remains a glaring disconnect between the two lines of research, and the other aim of this workshop is to find concrete directions toward bridging this divide. Many of the algorithms with strong statistical guarantees either make strong modeling assumptions or suffer from computational inefficiencies while many algorithms achieving empirical successes are less amenable to theoretical analysis. By bringing both theoreticians and practitioners together, we hope to identify future research directions that address this disconnect.

We are looking for contributed talks/posters on interactive learning defined broadly, including but not limited to:

1. Robust interactive learning procedures.

2. Computationally efficient interactive learning algorithms.

3. Empirical success stories of interactive learning algorithms.

4. New interactive models (for eg: crowdsourcing).

5. Connections between active, online, reinforcement and other sequential learning models.

We hope to make concrete progress toward bridging the gap between theory and practice in active learning.


Dual Submission Policy: Our workshop will not have published proceedings and workshop papers are intended for discussion rather than formal peer-review. Hence, we invite short versions of papers published at (or submitted to) other recent conferences. However, we must be informed about all such dual submissions.



Submission Instructions

  • Email as attachment to icmlalworkshop@gmail.com, with subject as "ICML-ALW" followed by the title of your paper (to update the paper, reply to the same email with the updated attachment)
  • The final date for submissions is May 1, 2015 (11:59pm UTC).
  • Page limit: 4 pages (without references)
  • Please use the ICML 2015 submission format
  • The submission need not be anonymized