“When a measure becomes a target, it ceases to be a good measure.” GoodHart’s Law Stochastic Gradient Descent (SGD) has been responsible for many of the most outstanding achievements in machine learning. The objective of SGD is to optimise a target in the form of a loss function. But SGD fails in finding ‘standard’ loss…

The post How Goodhart’s Law Can Save Machine Learning appeared first on Analytics India Magazine.