Max Zhu, Jian Yao, Marcus Mynatt, Hubert Pugzlys, Shuyi Li, Sergio Bacallado, Qingyuan Zhao, Chunjing Jia
{"title":"利用高斯过程主动学习发现复杂相图","authors":"Max Zhu, Jian Yao, Marcus Mynatt, Hubert Pugzlys, Shuyi Li, Sergio Bacallado, Qingyuan Zhao, Chunjing Jia","doi":"arxiv-2409.07042","DOIUrl":null,"url":null,"abstract":"We introduce a Bayesian active learning algorithm that efficiently elucidates\nphase diagrams. Using a novel acquisition function that assesses both the\nimpact and likelihood of the next observation, the algorithm iteratively\ndetermines the most informative next experiment to conduct and rapidly discerns\nthe phase diagrams with multiple phases. Comparative studies against existing\nmethods highlight the superior efficiency of our approach. We demonstrate the\nalgorithm's practical application through the successful identification of the\nentire phase diagram of a spin Hamiltonian with antisymmetric interaction on\nHoneycomb lattice, using significantly fewer sample points than traditional\ngrid search methods and a previous method based on support vector machines. Our\nalgorithm identifies the phase diagram consisting of skyrmion, spiral and\npolarized phases with error less than 5% using only 8% of the total possible\nsample points, in both two-dimensional and three-dimensional phase spaces.\nAdditionally, our method proves highly efficient in constructing\nthree-dimensional phase diagrams, significantly reducing computational and\nexperimental costs. Our methodological contributions extend to\nhigher-dimensional phase diagrams with multiple phases, emphasizing the\nalgorithm's effectiveness and versatility in handling complex, multi-phase\nsystems in various dimensions.","PeriodicalId":501369,"journal":{"name":"arXiv - PHYS - Computational Physics","volume":"59 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Active Learning for Discovering Complex Phase Diagrams with Gaussian Processes\",\"authors\":\"Max Zhu, Jian Yao, Marcus Mynatt, Hubert Pugzlys, Shuyi Li, Sergio Bacallado, Qingyuan Zhao, Chunjing Jia\",\"doi\":\"arxiv-2409.07042\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We introduce a Bayesian active learning algorithm that efficiently elucidates\\nphase diagrams. Using a novel acquisition function that assesses both the\\nimpact and likelihood of the next observation, the algorithm iteratively\\ndetermines the most informative next experiment to conduct and rapidly discerns\\nthe phase diagrams with multiple phases. Comparative studies against existing\\nmethods highlight the superior efficiency of our approach. We demonstrate the\\nalgorithm's practical application through the successful identification of the\\nentire phase diagram of a spin Hamiltonian with antisymmetric interaction on\\nHoneycomb lattice, using significantly fewer sample points than traditional\\ngrid search methods and a previous method based on support vector machines. Our\\nalgorithm identifies the phase diagram consisting of skyrmion, spiral and\\npolarized phases with error less than 5% using only 8% of the total possible\\nsample points, in both two-dimensional and three-dimensional phase spaces.\\nAdditionally, our method proves highly efficient in constructing\\nthree-dimensional phase diagrams, significantly reducing computational and\\nexperimental costs. Our methodological contributions extend to\\nhigher-dimensional phase diagrams with multiple phases, emphasizing the\\nalgorithm's effectiveness and versatility in handling complex, multi-phase\\nsystems in various dimensions.\",\"PeriodicalId\":501369,\"journal\":{\"name\":\"arXiv - PHYS - Computational Physics\",\"volume\":\"59 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Computational Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07042\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Computational Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07042","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Active Learning for Discovering Complex Phase Diagrams with Gaussian Processes
We introduce a Bayesian active learning algorithm that efficiently elucidates
phase diagrams. Using a novel acquisition function that assesses both the
impact and likelihood of the next observation, the algorithm iteratively
determines the most informative next experiment to conduct and rapidly discerns
the phase diagrams with multiple phases. Comparative studies against existing
methods highlight the superior efficiency of our approach. We demonstrate the
algorithm's practical application through the successful identification of the
entire phase diagram of a spin Hamiltonian with antisymmetric interaction on
Honeycomb lattice, using significantly fewer sample points than traditional
grid search methods and a previous method based on support vector machines. Our
algorithm identifies the phase diagram consisting of skyrmion, spiral and
polarized phases with error less than 5% using only 8% of the total possible
sample points, in both two-dimensional and three-dimensional phase spaces.
Additionally, our method proves highly efficient in constructing
three-dimensional phase diagrams, significantly reducing computational and
experimental costs. Our methodological contributions extend to
higher-dimensional phase diagrams with multiple phases, emphasizing the
algorithm's effectiveness and versatility in handling complex, multi-phase
systems in various dimensions.