Learning when to garbage collect with random forests

Generational garbage collectors are one of the most common types of automatic memory management. We can minimize the costs they incur by carefully choosing the points in a program's execution at which they run. However, this decision is generally based on simple, crude heuristics. Instead, we train random forest classifiers to decide when to collect based on features gathered from a running program. This reduces the total cost of collection in both time and space. We demonstrate useful generalization of learned policies to unseen traces of the same program, showing this approach may be fruitful for further investigation.