arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.07512cond-mat.stat-mechcond-mat.dis-nnphysics.data-anq-bio.MNq-bio.QM
收藏

物理优化推理

Physically optimizing inference

Audrey Huang, Benjamin Sheldan, David A. Sivak, Matt Thomson

摘要:

数据在从基因组学到神经科学再到经济学的各个领域呈指数级增长。一个核心问题是:现代机器学习方法能否应用于基于大数据集构建细胞和大脑等自然系统的预测模型?在本文中,我们研究了当训练数据由物理系统的统计行为生成时,推理是如何受到影响的,因此不受实验者的直接控制。我们发展了一个信息论分析的自旋网络推理的典型问题。我们的分析揭示了自旋网络及其环境的物理性质在确定底层机器学习问题的难度方面所起的重要作用。具体来说,随机波动驱动系统探索一系列的配置,为学习算法提供“原始”信息,以构建准确的模型;但它们也模糊了网络状态之间的能量差异,从而降低了信息。这种竞争导致自旋网络通常具有内在的最佳温度,在该温度下,随机自旋波动为区分竞争模型提供最大信息,从而最大化推理效率。我们展示了一个简单的主动学习协议,它优化了网络温度,以提高推理效率,并大大提高了神经电路重建任务的推理效率。我们的研究结果揭示了物理和信息之间的基本联系,并展示了如何调整物理环境以优化机器学习的效率。

英文摘要:

Data is scaling exponentially in fields ranging from genomics to neuroscience to economics. A central question is: can modern machine learning methods be applied to construct predictive models of natural systems like cells and brains based on large data sets? In this paper, we examine how inference is impacted when training data is generated by the statistical behavior of a physical system, and hence outside direct control by the experimentalist. We develop an information-theoretic analysis for the canonical problem of spin-network inference. Our analysis reveals the essential role that the physical properties of the spin network and its environment play in determining the difficulty of the underlying machine learning problem. Specifically, stochastic fluctuations drive a system to explore a range of configurations providing `raw' information for a learning algorithm to construct an accurate model; yet they also blur energetic differences between network states and thereby degrade information. This competition leads spin networks to generically have an intrinsic optimal temperature at which stochastic spin fluctuations provide maximal information for discriminating among competing models, maximizing inference efficiency. We demonstrate a simple active learning protocol that optimizes network temperature to boost inference efficiency and dramatically increases the efficiency of inference on a neural circuit reconstruction task. Our results reveal a fundamental link between physics and information and show how the physical environment can be tuned to optimize the efficiency of machine learning.

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。

↑