Differentiable Self-Adaptive Learning Rate

no code implementations • 19 Oct 2022 • Bozhou Chen, Hongzhi Wang, Chenmin Ba

Learning rate adaptation is a popular topic in machine learning.

Differentiable Hyper-parameter Optimization

no code implementations • 29 Sep 2021 • Bozhou Chen, Hongzhi Wang, Chenmin Ba

We apply our method for the optimization of various neural network layers' hyper-parameters and compare it with multiple benchmark hyper-parameter optimization models.

Bayesian Optimization BIG-bench Machine Learning

Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameters

no code implementations • 3 Mar 2020 • Bozhou Chen, Kaixin Zhang, Longshen Ou, Chenmin Ba, Hongzhi Wang, Chunnan Wang

However, most machine learning algorithms are sensitive to the hyper-parameters.

BIG-bench Machine Learning