English

A theoretical framework for deep locally connected ReLU network

Machine Learning 2018-10-01 v1 Machine Learning

Abstract

Understanding theoretical properties of deep and locally connected nonlinear network, such as deep convolutional neural network (DCNN), is still a hard problem despite its empirical success. In this paper, we propose a novel theoretical framework for such networks with ReLU nonlinearity. The framework explicitly formulates data distribution, favors disentangled representations and is compatible with common regularization techniques such as Batch Norm. The framework is built upon teacher-student setting, by expanding the student forward/backward propagation onto the teacher's computational graph. The resulting model does not impose unrealistic assumptions (e.g., Gaussian inputs, independence of activation, etc). Our framework could help facilitate theoretical analysis of many practical issues, e.g. overfitting, generalization, disentangled representations in deep networks.

Keywords

Cite

@article{arxiv.1809.10829,
  title  = {A theoretical framework for deep locally connected ReLU network},
  author = {Yuandong Tian},
  journal= {arXiv preprint arXiv:1809.10829},
  year   = {2018}
}

Comments

Submitted to ICLR 2019

R2 v1 2026-06-23T04:21:29.730Z