Electronica AI’s team of data scientists work with big streams of data, transforming complex relationships into meaningful structures with high predictive accuracy.
WHAT WE DO
Using our foundation in machine learning and finance, we develop systems to validate, train and deploy efficient analytics tools.
We have developed a state of the art data science pipeline for analyzing dense time series data.
Our algorithms get smarter everyday, learning to stay ahead of the curve and to operate on noisy data.
Stochastic Hyperparameter Optimization Through Hypernetworks
Machine learning models are often tuned by nesting optimization of model weights inside the optimization of hyperparameters. We give a method to collapse this nested optimization into joint stochastic optimization of weights and hyperparameters. Our process trains a neural network to output approximately optimal weights as a function of hyperparameters. We show that our technique converges to locally optimal weights and hyperparameters for sufficiently large hypernetworks. We compare this method to standard hyperparameter optimization strategies and demonstrate its effectiveness for tuning thousands of hyperparameters.