Mathematical perspective on genetic algorithms with optimization guided operators
This paper introduces a general model of genetic algorithms and studies their optimization problems using reinforcement learning.
This paper introduces a new model of genetic algorithms and uses reinforcement learning to study their optimization problems, which is novel compared to prior work that uses random mutation and recombination operators.
Before reading this…
Applications
- →Optimization problems
- →Machine learning
To understand this paper, make sure you know these concepts first:
- Genetic algorithmsfind papers →
- Reinforcement learningfind papers →
Abstract
More Like ThisRecent work in ML applies genetic algorithms at inference time to iteratively improve solutions to optimization problems. The basic mutation and recombination operators involved are qualitatively different from those studied classically. Mutations are no longer random; an ML algorithm mutates a solution with the goal of improving an objective. Similarly, recombination is not based on random collages of parent solutions. Instead, it is an ML optimization-based operator whose goal is to synthesize improved solutions from its inputs. Thus, these mutation and recombination operators are more likely to improve the objective, but their computational cost is much higher. We introduce a general model of genetic algorithms and formulating optimization in this model as a query-complexity problem, using the language of reinforcement learning. We then study specialized models. We show that some optimization problems require generation, mutation, and recombination to be solved. We then obtain qualitatively tight algorithms for a family of problems within this framework that captures the nontrivial role of diversity in the solution pool, a key feature of practical ML genetic algorithms.