On The Robustness Of Noisy Ace Algorithm And Multi-Layer Residual Learning
2019 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT)(2019)
摘要
In this paper, we address the issue of computing the maximal correlation functions for jointly distributed high-dimensional random variables. In such cases, the operations in the alternative conditional expectation (ACE) algorithm can only be implemented by an approximated manner, which is modeled as a variational ACE algorithm with noise. We study the computational behaviors of this algorithm, where the optimal tradeoff between the learning rate, computation accuracy, and convergence rate is investigated. In addition, we establish a connection between the variational ACE algorithm and the residual learning architecture. Our results illustrate interesting interpretations of how multi-layer residual structure benefits function learning.
更多查看译文
关键词
learning rate,convergence rate,maximal correlation functions,high-dimensional random variables,alternative conditional expectation algorithm,computational behaviors,multilayer residual learning architecture,variational ACE algorithm
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络