Proceedings of the 3rd Workshop on Machine Learning and Systems最新文献

筛选

英文中文

MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder 蒙特卡罗树搜索是一个很好的电子图生成器

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2023-03-08 DOI: 10.48550/arXiv.2303.04651

Guoliang He, Zak Singh, Eiko Yoneki

{"title":"MCTS-GEB: Monte Carlo Tree Search is a Good E-graph Builder","authors":"Guoliang He, Zak Singh, Eiko Yoneki","doi":"10.48550/arXiv.2303.04651","DOIUrl":"https://doi.org/10.48550/arXiv.2303.04651","url":null,"abstract":"Rewrite systems [11, 16, 18] have been widely employing equality saturation [15], 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) [4] 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.","PeriodicalId":370204,"journal":{"name":"Proceedings of the 3rd Workshop on Machine Learning and Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121284746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards Practical Few-shot Federated NLP 走向实用的少镜头联邦NLP

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 2022-12-01 DOI: 10.1145/3578356.3592575

Dongqi Cai, Yaozong Wu, Haitao Yuan, Shangguang Wang, F. Lin, Mengwei Xu

引用次数: 3

Proceedings of the 3rd Workshop on Machine Learning and Systems 第三届机器学习与系统研讨会论文集

Proceedings of the 3rd Workshop on Machine Learning and Systems Pub Date : 1900-01-01 DOI: 10.1145/3578356

引用次数: 0

首页上一页