Demonstrating SubStrat: A Subset-Based Strategy for Faster AutoML on Large Datasets

Keyphrases

• AutoML 100%
• Subset-based 100%
• ML pipeline 50%
• Machine Learning System 25%
• Machine Learning Framework 25%
• Machine Learning Workflow 12%
• Search Space 12%
• Popular 12%
• Genetic Algorithm 12%
• Prediction Accuracy 12%
• Training Data 12%
• Manual Work 12%
• Real-life Dataset 12%
• Optimization Strategy 12%
• Dataset Size 12%
• Machine Learning Optimization 12%
• Configuration Search 12%
• Data Scientist 12%
• Pipeline Specification 12%
• Auto-sklearn 12%

Computer Science

• Large Data Set 100%
• Automated Machine Learning 100%
• Machine Learning 50%
• Learning Framework 25%
• Learning Process 12%
• Search Space 12%
• Training Dataset 12%
• Predictive Accuracy 12%
• Data Scientist 12%
• Optimization Strategy 12%