arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.16683astro-ph.SRcs.LG
收藏

基于主动学习的二元进化模拟计算效率分布

Active Learning for Computationally Efficient Distribution of Binary Evolution Simulations

Center for Interdisciplinary Exploration and Research in Astrophysics (CIERA)(天体物理学跨学科探索与研究中心(CIERA));University of Florida(佛罗里达大学);University of Glasgow(格拉斯哥大学);Northwestern University(西北大学);KU Leuven(鲁汶大学)
Kyle Akira Rocha, Jeff J. Andrews, Christopher P. L. Berry, Zoheyr Doctor, Aggelos K. Katsaggelos, Juan Gabriel Serra Pérez, Pablo Marchant, Vicky Kalogera, Sco… 展开作者

Kyle Akira Rocha, Jeff J. Andrews, Christopher P. L. Berry, Zoheyr Doctor, Aggelos K. Katsaggelos, Juan Gabriel Serra Pérez, Pablo Marchant, Vicky Kalogera, Scott Coughlin, Simone S. Bavera, Aaron Dotter, Tassos Fragos, Konstantinos Kovlakas, Devina Misra, Zepei Xing, Emmanouil Zapartas

摘要:

双星经历了各种相互作用和演化阶段,对于预测和解释观测到的性质至关重要。具有完整恒星结构和进化模拟的二元种群合成计算成本很高,需要大量的质量转移序列。最近开发的二进制人口合成代码POSYDON采用网格的MESA双星模拟,然后插入大规模人口的大规模双星模型。计算高密度直线网格模拟的传统方法是不可扩展的高维网格,占金属丰度,旋转和偏心率的范围。我们提出了一种新的主动学习算法psy-cris,它在数据收集过程中使用机器学习来自适应地、迭代地选择要运行的目标模拟,从而生成自定义的高性能训练集。我们在一个玩具问题上测试了psy-cris,发现得到的训练集比常规或随机采样的网格需要更少的模拟来进行准确的分类和回归。我们进一步应用psy-cris的目标问题,建立一个动态网格的MESA模拟,我们证明,即使没有微调,一个模拟集只有$\sim 1/4$的大小的直线网格是足以达到相同的分类精度。我们预计,当算法参数针对目标应用程序进行优化时,将获得进一步的收益。我们发现,优化分类只可能导致性能损失的回归,反之亦然。降低生成网格的计算成本将使未来版本的POSYDON能够覆盖更多的输入参数,同时保持插值精度。

英文摘要:

Binary stars undergo a variety of interactions and evolutionary phases, critical for predicting and explaining observed properties. Binary population synthesis with full stellar-structure and evolution simulations are computationally expensive requiring a large number of mass-transfer sequences. The recently developed binary population synthesis code POSYDON incorporates grids of MESA binary star simulations which are then interpolated to model large-scale populations of massive binaries. The traditional method of computing a high-density rectilinear grid of simulations is not scalable for higher-dimension grids, accounting for a range of metallicities, rotation, and eccentricity. We present a new active learning algorithm, psy-cris, which uses machine learning in the data-gathering process to adaptively and iteratively select targeted simulations to run, resulting in a custom, high-performance training set. We test psy-cris on a toy problem and find the resulting training sets require fewer simulations for accurate classification and regression than either regular or randomly sampled grids. We further apply psy-cris to the target problem of building a dynamic grid of MESA simulations, and we demonstrate that, even without fine tuning, a simulation set of only $\sim 1/4$ the size of a rectilinear grid is sufficient to achieve the same classification accuracy. We anticipate further gains when algorithmic parameters are optimized for the targeted application. We find that optimizing for classification only may lead to performance losses in regression, and vice versa. Lowering the computational cost of producing grids will enable future versions of POSYDON to cover more input parameters while preserving interpolation accuracies.

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。

↑