Online gradient method with smoothing ℓ0 regularization for feedforward neural networks
Sign Up to like & getrecommendations! Published in 2017 at "Neurocomputing"
DOI: 10.1016/j.neucom.2016.10.057
Abstract: źp regularization has been a popular pruning method for neural networks. The parameter p was usually set as 0 < p ź 2 in the literature, and practical training algorithms with ź0 regularization are lacking… read more here.
Keywords: neural networks; smoothing regularization; method; regularization ... See more keywords
Online Learning With Inexact Proximal Online Gradient Descent Algorithms
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Signal Processing"
DOI: 10.1109/tsp.2018.2890368
Abstract: We consider nondifferentiable dynamic optimization problems such as those arising in robotics and subspace tracking. Given the computational constraints and the time-varying nature of the problem, a low-complexity algorithm is desirable, while the accuracy of… read more here.
Keywords: gradient descent; proximal online; online; inexact proximal ... See more keywords