Asymptotic Analysis of higher-order scattering transform of Gaussian processes

Gi Ren Liu, Yuan Chung Sheu, Hau Tieng Wu

研究成果: Article同行評審


We analyze the scattering transform with the quadratic nonlinearity (STQN) of Gaussian processes without depth limitation. STQN is a nonlinear transform that involves a sequential interlacing convolution and nonlinear operators, which is motivated to model the deep convolutional neural network. We prove that with a proper normalization, the output of STQN converges to a chi-square process with one degree of freedom in the finite dimensional distribution sense, and we provide a total variation distance control of this convergence at each time that converges to zero at an exponential rate. To show these, we derive a recursive formula to represent the intricate nonlinearity of STQN by a linear combination of Wiener chaos, and then apply the Malliavin calculus and Stein’s method to achieve the goal.

期刊Electronic Journal of Probability
出版狀態Published - 2022

All Science Journal Classification (ASJC) codes

  • 統計與概率
  • 統計、概率和不確定性


深入研究「Asymptotic Analysis of higher-order scattering transform of Gaussian processes」主題。共同形成了獨特的指紋。