While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, another trend in AutoML is to focus on neural architecture search. To bring the best of these two worlds together, we developed Auto-PyTorch, which jointly and robustly optimizes the network architecture and the training hyperparameters to enable fully automated deep learning (AutoDL). Auto-PyTorch is mainly developed to support tabular data (classification, regression) and time series data (forecasting). The newest features in Auto-PyTorch for tabular data are described in the paper "Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL" (see below for bibtex ref). Details about Auto-PyTorch for multi-horizontal time series forecasting tasks can be found in the paper "Efficient Automated Deep Learning for Time Series Forecasting" (also see below for bibtex ref).
Features
- Validate input data: Process each data type, e.g. encoding categorical data, so that Auto-Pytorch can handled
- Create dataset: Create a dataset that can be handled in this API with a choice of cross validation or holdout splits
- Tabular dataset *1: Train each algorithm in the predefined pool with a fixed hyperparameter configuration
- Time Series Forecasting dataset : Train a dummy predictor that repeats the last observed value in each series
- Determine budget and cut-off rules by Hyperband
- Sample a pipeline hyperparameter configuration *2 by SMAC