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 2010.14765cs.LGcs.ITmath.ITmath.OCstat.ML
收藏

从速率降低原理看深度网络

Deep Networks from the Principle of Rate Reduction

Department of EECS, University of California, Berkeley(加州大学伯克利分校电气工程与计算机科学系);Department of Electrical Engineering and Data Science Institute, Columbia University(哥伦比亚大学电气工程与数据科学研究所);Department of Applied Physics and Applied Mathematics, Columbia University(哥伦比亚大学应用物理与应用数学系)

Kwan Ho Ryan Chan, Yaodong Yu, Chong You, Haozhi Qi, John Wright, Yi Ma

摘要:

这项工作试图从速率降低和(移位)不变分类的原理来解释现代深度(卷积)网络。我们发现,用于优化学习特征的速率降低的基本迭代梯度上升方案自然会导致多层深度网络,每层一次迭代。分层结构,线性和非线性算子,甚至网络的参数都是通过模拟梯度方案以前向传播方式逐层显式构建的。这个“白盒”网络的所有组件都具有精确的优化、统计和几何解释。这个原则性框架也揭示和证明了多通道提升和稀疏编码在深度网络早期阶段的作用。此外,当我们强制分类为严格的平移不变时,由此导出的网络的所有线性算子自然成为多通道卷积。推导还表明,这样的卷积网络在谱域中的构造和学习效率要高得多。我们的初步模拟和实验表明,即使没有任何反向传播训练,这样构建的深度网络也已经可以学习到良好的区分表示。

英文摘要:

This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of learned features naturally leads to a multi-layer deep network, one iteration per layer. The layered architectures, linear and nonlinear operators, and even parameters of the network are all explicitly constructed layer-by-layer in a forward propagation fashion by emulating the gradient scheme. All components of this "white box" network have precise optimization, statistical, and geometric interpretation. This principled framework also reveals and justifies the role of multi-channel lifting and sparse coding in early stage of deep networks. Moreover, all linear operators of the so-derived network naturally become multi-channel convolutions when we enforce classification to be rigorously shift-invariant. The derivation also indicates that such a convolutional network is significantly more efficient to construct and learn in the spectral domain. Our preliminary simulations and experiments indicate that so constructed deep network can already learn a good discriminative representation even without any back propagation training.

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。

↑