Oleg Zabluda's blog
Thursday, July 12, 2018
 
Dropout as a Low-Rank Regularizer for Matrix Factorization (2018) Jacopo Cavazza, et al.
Dropout as a Low-Rank Regularizer for Matrix Factorization (2018) Jacopo Cavazza, et al.
"""
We demonstrate the equivalence between dropout and a fully deterministic model for matrix factorization (MF) in which the factors are regularized by the sum of the product of squared Euclidean norms of the columns. Additionally, we inspect the case of a variable sized factorization and we prove that dropout achieves the global minimum of a convex approximation problem with (squared) nuclear norm regularization. As a result, we conclude that dropout can be used as a low-rank regularizer with data dependent singular-value thresholding.
"""
https://arxiv.org/abs/1710.05092
https://arxiv.org/abs/1710.05092

Labels:


- posted by Oleg Zabluda @ 1:40 PM | permalink | | | technorati | bloglines | feedster
| |

Home

Powered by Blogger