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 2003.13438cs.LGstat.ML
收藏

核心机制下的知识转移分析

Analysis of Knowledge Transfer in Kernel Regime

Chalmers University of Technology(查尔姆斯理工大学);Indian Institute of Science(印度科学学院)

Arman Rahbar, Ashkan Panahi, Chiranjib Bhattacharyya, Devdatt Dubhashi, Morteza Haghir Chehreghani

摘要:

知识转移被证明是训练神经分类器的一种非常成功的技术:与地面真实数据一起,它使用“教师”网络获得的“特权信息”(PI)来训练“学生”网络。据观察,分类器通过知识转移学习得更快,更可靠。然而,很少或根本没有对这一现象进行理论分析。为了弥合这一差距,我们建议通过正规化的教师和学生与PI提供的教师之间的配合,知识转移的问题。使用动力系统理论的工具,我们表明,当学生是一个非常广泛的两层网络,我们可以分析它的内核政权,并表明它是能够PI和给定的数据之间的插值。这一特征揭示了新的光之间的关系的培训错误和能力的学生相对于教师。本文的另一个贡献是对学生网络的收敛性进行了定量的描述。我们证明了教师减少了学生学习所需的迭代次数,从而提高了学生的泛化能力。我们给出了相应的实验分析,验证了理论结果,并产生额外的见解。

英文摘要:

Knowledge transfer is shown to be a very successful technique for training neural classifiers: together with the ground truth data, it uses the "privileged information" (PI) obtained by a "teacher" network to train a "student" network. It has been observed that classifiers learn much faster and more reliably via knowledge transfer. However, there has been little or no theoretical analysis of this phenomenon. To bridge this gap, we propose to approach the problem of knowledge transfer by regularizing the fit between the teacher and the student with PI provided by the teacher. Using tools from dynamical systems theory, we show that when the student is an extremely wide two layer network, we can analyze it in the kernel regime and show that it is able to interpolate between PI and the given data. This characterization sheds new light on the relation between the training error and capacity of the student relative to the teacher. Another contribution of the paper is a quantitative statement on the convergence of student network. We prove that the teacher reduces the number of required iterations for a student to learn, and consequently improves the generalization power of the student. We give corresponding experimental analysis that validates the theoretical results and yield additional insights.

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。

↑