Authors:Kartik Chandra,Erik Meijer,Samantha Andow,Emilio Arroyo-Fang,Irene Dea,Johann George,Melissa Grueter,Basil Hosmer, (Steffi Stumpos,Alanna Tempest,Shannon Yang
Submitted on (Sep 2019)
Abstract:Working with any gradient -based machine learning algorithm involves the tedious task of tuning the optimizer’s hyperparameters, such as the learning rate. There exist many techniques for automated hyperparameter optimization, but they typically introduce even more hyperparameters to control the hyperparameter optimization process. We propose to instead learn the hyperparameters themselves by gradient descent, and furthermore to learn the hyper-hyperparameters by gradient descent as well, and so on ad infinitum. As these towers of gradient-based optimizers grow, they become significantly less sensitive to the choice of top-level hyperparameters, hence decreasing the burden on the user to search for optimal values.
Submission history
From: Erik Meijer [view email]
[v1]Sun, (Sep) 21: 41 : 49 UTC (538 KB
GIPHY App Key not set. Please check settings