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 1901.02220cs.LGcs.ITmath.ITstat.ML
收藏

深度神经网络逼近理论

Deep Neural Network Approximation Theory

University of Vienna(维也纳大学);ETH Zurich(苏黎世联邦理工学院)

Dennis Elbrächter, Dmytro Perekrestenko, Philipp Grohs, Helmut Bölcskei

摘要:

本文通过描述如果对学习算法和训练数据的量不施加约束的情况下的可能性,来开发深度神经网络学习的基本限制。具体地说,我们认为通过深层神经网络的柯尔莫哥洛夫最优逼近的指导主题是一个关系的复杂性的函数(类)被近似和复杂性的近似网络的连接和存储网络拓扑结构和相关的量化权重的内存要求。我们开发的理论建立了深度网络是明显不同的函数类的Kolmogorov最优逼近,例如Besov空间和调制空间中的单位球。此外,深度网络提供指数近似精度-即,近似误差在乘法运算、多项式、正弦函数和某些平滑函数的网络中的非零权重的数量上呈指数衰减。此外,即使对于一维振荡纹理和维尔斯特拉斯函数(一种分形函数)也是如此,这两种函数都没有先前已知的方法实现指数近似精度。我们还表明,在足够光滑的函数的近似,有限宽度的深度网络需要严格小于有限深度的宽网络的连接。

英文摘要:

This paper develops fundamental limits of deep neural network learning by characterizing what is possible if no constraints are imposed on the learning algorithm and on the amount of training data. Concretely, we consider Kolmogorov-optimal approximation through deep neural networks with the guiding theme being a relation between the complexity of the function (class) to be approximated and the complexity of the approximating network in terms of connectivity and memory requirements for storing the network topology and the associated quantized weights. The theory we develop establishes that deep networks are Kolmogorov-optimal approximants for markedly different function classes, such as unit balls in Besov spaces and modulation spaces. In addition, deep networks provide exponential approximation accuracy - i.e., the approximation error decays exponentially in the number of nonzero weights in the network - of the multiplication operation, polynomials, sinusoidal functions, and certain smooth functions. Moreover, this holds true even for one-dimensional oscillatory textures and the Weierstrass function - a fractal function, neither of which has previously known methods achieving exponential approximation accuracy. We also show that in the approximation of sufficiently smooth functions finite-width deep networks require strictly smaller connectivity than finite-depth wide networks.

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。

↑