How Goodhart's Law Can Save Machine Learning Research

"When a measure becomes a target, it ceases to be a good measure." 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 functions in a few settings as it converges to the'easy' solutions. As we see above, when classifying sheep, the network learns to use the green background to identify the sheep present.