Features

How Auger Leads the Way

AUGER CHOOSES THE APPROPRIATE OPTIMIZER BASED ON THE DATASET

Auger appropriately chooses which optimizer to use based on characteristics of the dataset which includes our own and several off the shelf algorithms optimization:
  • Tree Parzen Estimators
  • Partical Swarm
  • Nelder Mead
  • Auger Optimizer
features section-1

PROPRIETARY OPTIMIZERS THAT OUTPERFORM OTHER KNOWN OPEN OPTIMIZERS


Auger has several proprietary optimizers that outperform the more widely known open algorithms cited above on certain datasets.

Most Bayesian optimization approaches (such as HyperOpt and HyperBand) rely purely on estimates of the accuracy of the trained algorithm.

Auger explores the space of possible algorithms and hyperparameters as an infinite time problem that we need to define the problem as finding the best model within a bounded timeframe.

Auger has a patent-pending system that leverages both accuracy and time to train to choose the model with the best chance of the highest accuracy within the selected time-bound, giving you faster and more reliable results.
features section-2

DON’T JUST ENSEMBLE MODELS, ENSEMBLE OPTIMIZERS


  • Auger combines leading complementary models into ensembles to get the highest accuracy.
  • Auger combines approaches of optimizers to find better-suggested models faster.
  • Auger’s proprietary optimizers combine well with more commonly known approaches which outperform two similar known optimizers for both HyperOpt and HyperBand.
features section-3