How many neurons do we need? A refined analysis for shallow networks trained with gradient descent

RT @moskitos_bite: 📢Our paper just got out: For early stopped GD we derive minimax rates of convergence. On our way, we precisely keep t…

📢Our paper just got out: For early stopped GD we derive minimax rates of convergence. On our way, we precisely keep track of the number of hidden neurons required for generalization and improve over existing results. https://t.co/TmJcXqvO7H