Research Report on Automatic Synthesis of Local Search Neighborhood Operators

Constraint Programming (CP) and Local Search (LS) are different paradigms for dealing with combinatorial search and optimization problems. Their complementary features motivated researchers to create hybrid CP/LS solutions, maintaining both the modeling capabilities of CP and the computational advantages of the heuristic-based LS approach. Research presented in this report is focused on developing a novel method to infer an efficient LS neighborhood operator based on the problem structure, as modeled in the CP paradigm. We consider a limited formal language that we call a Neighborhood Definition Language, used to specify the neighborhood operators in a fine-grained and declarative manner. Together with Logic Programming runtime called Noodle, it allows to automatically synthesize complex operators using a Grammar Evolution algorithm.

Generating Local Search Neighborhood with Synthesized Logic Programs

Local Search meta-heuristics have been proven a viable approach to solve difficult optimization problems. Their performance depends strongly on the search space landscape, as defined by a cost function and the selected neighborhood operators. In this paper we present a logic programming based framework, named Noodle, designed to generate bespoke Local Search neighborhoods tailored to specific discrete optimization problems. The proposed system consists of a domain specific language, which is inspired by logic programming, as well as a genetic programming solver, based on the grammar evolution algorithm. We complement the description with a preliminary experimental evaluation, where we synthesize efficient neighborhood operators for the traveling salesman problem, some of which reproduce well-known results.