Proxima: accelerating the integration of machine learning in atomistic simulations
Proxima: accelerating the integration of machine learning in atomistic simulations
复制标题
DOI：
10.1145/3447818.3460370
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Yuliana Zamora;Logan T. Ward;G. Sivaraman;Ian T. Foster;H. Hoffmann
中科院分区：
文献类型：
--
作者：
Yuliana Zamora;Logan T. Ward;G. Sivaraman;Ian T. Foster;H. Hoffmann
原子规模的模拟是突出的科学应用，需要重复执行计算昂贵的例程来计算系统的势能。先前的工作表明，这些昂贵的例程可以用机器学习的替代近似代替，以加速模拟，但以整体精度为代价。速度和准确性的确切平衡取决于替代模型工作流程和科学本身的特定配置，并且先前的工作使科学家可以找到一种为他们的科学问题提供所需准确性的配置。不幸的是，由于基础系统动力学，很少有单个替代配置为整个模拟提供最佳的精度/延迟权衡。在实践中，科学家必须选择保守的配置，以便准确性始终是可以接受的，可能会加速的。作为替代方案，我们提出了Proxima，这是一种系统和自动化的方法，用于动态调整替代模型配置，以响应正在进行的模拟中的实时反馈。 Proxima估计在迭代模拟的每个步骤中应用替代近似值的不确定性。使用此信息，可以动态调整特定的替代配置，以确保最大的加速，同时维持所需的精度度量。我们使用Monte Carlo采样应用程序评估Proxima，并发现Proxima尊重广泛的用户定义精度目标，而相对于标准的加速度相对于标准
Atomistic-scale simulations are prominent scientific applications that require the repetitive execution of a computationally expensive routine to calculate a system's potential energy. Prior work shows that these expensive routines can be replaced with a machine-learned surrogate approximation to accelerate the simulation at the expense of the overall accuracy. The exact balance of speed and accuracy depends on the specific configuration of the surrogate-modeling workflow and the science itself, and prior work leaves it up to the scientist to find a configuration that delivers the required accuracy for their science problem. Unfortunately, due to the underlying system dynamics, it is rare that a single surrogate configuration presents an optimal accuracy/latency trade-off for the entire simulation. In practice, scientists must choose conservative configurations so that accuracy is always acceptable, forgoing possible acceleration. As an alternative, we propose Proxima, a systematic and automated method for dynamically tuning a surrogate-modeling configuration in response to real-time feedback from the ongoing simulation. Proxima estimates the uncertainty of applying a surrogate approximation in each step of an iterative simulation. Using this information, the specific surrogate configuration can be adjusted dynamically to ensure maximum speedup while sustaining a required accuracy metric. We evaluate Proxima using a Monte Carlo sampling application and find that Proxima respects a wide range of user-defined accuracy goals while achieving speedups of 1.02--5.5X relative to a standard