Call for papers - DSO workshop at IJCAI ‘19

Submission deadline: May 17, 2019

Data Science Meets Optimisation (DSO) Workshop at IJCAI-19
August 10-16, 2019, Macao, China

Submission deadline: May 17, 2019
Notification of acceptance: June 10, 2019

Data science and optimisation are closely related. On the one hand, many problems in data science can be solved using optimisers, on the other hand optimisation problems stated through classical models such as those from mathematical programming cannot be considered independent of historical data. Examples are ample. Machine learning often relies on optimisation techniques such as linear or integer programming. Algorithms may be complete, approximative or heuristic and may be applied in on-line or off line settings. Reasoning systems have been applied to constrained pattern and sequence mining tasks. A parallel development of metaheuristic approaches has taken place in the domains of data mining and machine learning. In the last decades, methods aimed at high level combinatorial optimisation have been shown to strongly profit from configuration and tuning tools building on historical data. Algorithm selection has since the seventies of the previous century been considered as a tool to select the most appropriate algorithm for a given instance. Empirical model learning uses machine learning models to approximate the behaviour of a system, and such empirical models can be embedded into an optimisation model for efficiently finding an optimal system configuration.

The aim of the workshop is to organize an open discussion and exchange of ideas by researchers from Data Science and Operations Research domains in order to identify how techniques from these two fields can benefit each other. The program committee invites submissions that include but are not limited to the following topics:

-  Applying data science and machine learning methods to solve combinatorial optimisation problems, such as algorithm selection based on historical data, speeding up (or driving) the search process using machine learning, and handling uncertainties of prediction models for decision-making.
-   Using optimisation algorithms in developing machine learning models: formulating the problem of learning predictive models as MIP, constraint programming (CP), or satisfiability (SAT). Tuning machine learning models using search algorithms and meta-heuristics. Learning in the presence of constraints.
-    Embedding methods: combining machine learning with combinatorial optimisation, model transformations and solver selection, reasoning over Machine Learning models.
-    Formal analysis of Machine Learning models via optimisation or constraint satisfaction techniques: safety checking and verification via SMT or MIP, generation of adversarial examples via similar combinatorial techniques.
-    Computing explanations for ML model via techniques developed for optimisation or constraint reasoning systems
-    Applications of integration of techniques of data science and optimisation.

We invite the following submissions (all in the IJCAI proceedings format, see: ):

- Submission of original work up to 8 pages in length.
- Submission of work in progress (with preliminary results) and position papers, up to 6 pages in length.
- Published journal/conference papers in the form of a 2-pages abstract.
The program committee will select the papers to be presented at the workshop according to their suitability to the aims. Contributors will be invited to submit extended articles to a post-conference special issue.

Submissions through:

Patrick De Causmaecker (KU Leuven, BE),
Michele Lombardi (University of Bologna, IT),
Yingqian Zhang (TU Eindhoven, NL),