Asymptotic Analysis of higher-order scattering transform of Gaussian processes
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.
Duke Scholars
Published In
DOI
EISSN
Publication Date
Volume
Related Subject Headings
- Statistics & Probability
- 0105 Mathematical Physics
- 0104 Statistics
Citation
Published In
DOI
EISSN
Publication Date
Volume
Related Subject Headings
- Statistics & Probability
- 0105 Mathematical Physics
- 0104 Statistics