MCTS-GEB：蒙特卡洛树搜索是优秀的 E-graph 构建器
MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder
AI总结：
本文提出 MCTS-GEB，利用强化学习和 MCTS 规划 e-graph 构建，以消除未饱和情况下的阶段排序问题，并在两个领域最高实现 49 倍性能提升。
摘要：
重写系统 [6, 10, 12] 已广泛采用等式饱和（equality saturation）[9]，这是一种优化方法，使用饱和的 e-graph 同时表示所有可能的重写序列，然后从中提取最优序列。因此，它可以通过避免阶段排序问题获得最优结果。然而，我们观察到，当 e-graph 未饱和时，它无法表示所有可能的重写机会，因此阶段排序问题会在 e-graph 的构建阶段重新出现。为解决该问题，我们提出 MCTS-GEB，这是一种领域通用的重写系统，将强化学习（RL）应用于 e-graph 构建。其核心是，MCTS-GEB 使用蒙特卡洛树搜索（MCTS）[3] 高效规划最优的 e-graph 构建，因此能够在构建阶段有效消除阶段排序问题，并在合理时间内取得更好性能。在两个不同领域的评估表明，MCTS-GEB 相比最先进的重写系统最高可快 49 倍，同时优化通常可在一小时内完成，表明 MCTS-GEB 是下一代重写系统颇具前景的构建模块。
英文摘要：
Rewrite systems [6, 10, 12] have been widely employing equality saturation [9], which is an optimisation methodology that uses a saturated e-graph to represent all possible sequences of rewrite simultaneously, and then extracts the optimal one. As such, optimal results can be achieved by avoiding the phase-ordering problem. However, we observe that when the e-graph is not saturated, it cannot represent all possible rewrite opportunities and therefore the phase-ordering problem is re-introduced during the construction phase of the e-graph. To address this problem, we propose MCTS-GEB, a domain-general rewrite system that applies reinforcement learning (RL) to e-graph construction. At its core, MCTS-GEB uses a Monte Carlo Tree Search (MCTS) [3] to efficiently plan for the optimal e-graph construction, and therefore it can effectively eliminate the phase-ordering problem at the construction phase and achieve better performance within a reasonable time. Evaluation in two different domains shows MCTS-GEB can outperform the state-of-the-art rewrite systems by up to 49x, while the optimisation can generally take less than an hour, indicating MCTS-GEB is a promising building block for the future generation of rewrite systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
