Constraint Optimisation and Applications. ECMLPKDD 2019 Tutorial: Data Mining and Machine Learning using Constraint Programming. About the Tutorial In recent years it has been realized that many data mining and machine learning problems, especially unsupervised ones, can be formalized as discrete constraint satisfaction and optimization problems. This tutorial provides a detailed overview of the use of constraint solving technology, such as constraint programming, SAT solvers, and MIP solvers, to solve these problems. After a short introduction to different types of solvers, we will provide an overview of a number of different machine learning and data mining problems and how they can be solved using these solvers.
Constraints in Python. Python and its scientific toolkits are generally considered as accessible and easy-to-start with, as well as encouraging prototyping and rapid development. What is the state of CP modeling in Python? And what are succesful approaches in the wider constraint community? How can we learn from each other and build on each other? To stimulate this discussion, we are hosting 4 exciting talks across 4 different constraint solving paradigms: Talks were 30-40 minutes, followed by open discussion. These talks are organized as part of a CPpy hackathon in preparation for Tias Guns' ERC Consolidator grant 'Conversational Human-Aware Technology for Optimisation' Mon 22 Feb, 10:00-11:00 CET: CP modelling in python: challenges and perspectives (NumberJack, PyCSP3, MiniZinc-Python and CPpy authors) Tue 23 Feb, 17:30-18:30 CET: CVXPY: A rewriting system for convex optimization (Akshay Agrawal, Stanford Universtiy, US)
Constraints, Consistency, and Complexity. Philippe Laborie’s Presentations on SlideShare.