Call for Papers

We invite submissions of full papers (max 8 pages excluding references) as well as work-in-progress, position, and challenging problems papers (max 4 pages excluding references). Papers must be formatted using the ICML template and submitted online via EasyChair.  Accepted papers will either be selected for a short oral presentation or a poster presentation. 

While original contributions are preferred, we also invite submissions of high-quality work that has recently been published in other venues.

Topics of interest include but are not limited to:

  • Novel tractable model classes
  • Extensions of existing tractable model classes: 
    • Novel structure and parameter learning algorithms 
    • Pushing the expressive power of tractable model classes 
    • More efficient inference algorithms, implementations 
  • Tractable statistical relational formalisms: 
    • Tractable Markov logic (TML) 
    • Probabilistic soft logic (PSL) 
    • Tractable probabilistic knowledge and databases 
    • Tractability through lifted inference 
  • Properties rendering inference and/or learning tractable with an emphasis on alternatives to treewidth 
    • Submodularity, concavity, convexity 
    • Chordality, perfectness of graphical models 
    • Model symmetries such as (fractional) automorphisms 
    • Notions of exchangeability 
  • Tractability of structure and parameter learning versus tractability of inference: 
    • Tractable learning via tractable inference 
    • Notions of tractable learning (PAC, etc.) 
    • Bridging the gap between tractability notions in AI/ML and statistics 
  • Approximate inference with polynomial approximation guarantees: 
    • Greedy algorithms with approximation guarantees 
    • Local search algorithms with approximation guarantees 
    • Sampling algorithms with approximation guarantees 
  • Applications of tractable model classes: 
    • Information extraction 
    • Data integration 
    • Computer vision 
    • Computational biology 
    • Natural language processing 
    • etc.