AutoML Research

PyGX is a versatile library that not only simplifies the implementation of AutoML applications but is also powerful enough to facilitate complex AutoML and ML research. Its capability and flexibility have been demonstrated in several academic papers.

Papers with code

• Evolving Reinforcement Learning algorithms, ICLR 2021 · code
• PyGX: Efficiently Exchanging ML Ideas as Code, 2022 · code

Papers

• PyGX: Symbolic Programming for Automated Machine Learning, NeurIPS 2020
• AutoHAS: Efficient Hyperparameter and Architecture Search, ICLR 2021 NAS workshop
• Towards the Co-design of Neural Networks and Accelerators, MLSys 2022
• Deepfusion: Lidar-camera Deep Fusion for Multi-modal 3D Object Detection, CVPR 2022
• ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning, CoRR 2021