AI RESEARCH
From Regression to Inference: Meta-Learning Predictors for Neural Architecture Search
arXiv CS.LG
•
ArXi:2605.09290v1 Announce Type: new Prediction-based approaches are widely used in neural architecture search (NAS), where a predictor estimates the performance of candidate architectures to guide selection. However, existing predictors are typically trained via supervised regression on limited samples, leading to overfitting and poor generalization to unseen architectures.