Effective Regularization Through Loss-Function Metalearning

2 Oct 2020  ·  Santiago Gonzalez, Risto Miikkulainen ·

Evolutionary optimization, such as the TaylorGLO method, can be used to discover novel, customized loss functions for deep neural networks, resulting in improved performance, faster training, and improved data utilization. A likely explanation is that such functions discourage overfitting, leading to effective regularization. This paper demonstrates theoretically that this is indeed the case for TaylorGLO: Decomposition of learning rules makes it possible to characterize the training dynamics and show that the loss functions evolved by TaylorGLO balance the pull to zero error, and a push away from it to avoid overfitting. They may also automatically take advantage of label smoothing. This analysis leads to an invariant that can be utilized to make the metalearning process more efficient in practice; the mechanism also results in networks that are robust against adversarial attacks. Loss-function evolution can thus be seen as a well-founded new aspect of metalearning in neural networks.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here