Auto-PyTorch
Automatic neural architecture search and hyperparameter optimization for PyTorch, focusing on tabular data and time series forecasting.
What is Auto-PyTorch?
Auto-PyTorch is an automated deep learning framework that automatically searches for the best neural network architecture and hyperparameters for a given dataset. It specifically targets tabular data (classification and regression) and time series forecasting tasks, eliminating the need for manual model design and tuning. The framework uses multi-fidelity meta-learning and portfolio-based warm-starting to efficiently deliver robust models.
Data scientists and machine learning engineers working with tabular or time series data who want to leverage deep learning without extensive manual architecture design and hyperparameter tuning.
Developers choose Auto-PyTorch for its fully automated approach to deep learning, combining neural architecture search with hyperparameter optimization in a single robust framework. It stands out with its specific optimization for tabular and time series data, efficient multi-fidelity search, and ensemble building capabilities.
Overview
Automatic architecture search and hyperparameter optimization for PyTorch
Use Cases
Best For
- Automating deep learning model development for tabular classification tasks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
