Neural Complexity Measures
Yoonho Lee, Juho Lee, Sung Ju Hwang, Eunho Yang, Seungjin Choi
While various complexity measures for diverse model classes have been proposed, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven to be challenging. We propose Neural Complexity (NC), an alternative data-driven approach that meta-learns a scalar complexity measure through interactions with a large number of heterogeneous tasks. The trained NC model can be added to the standard training loss to regularize any task learner under standard learning frameworks. We contrast NC’s approach against existing manually-designed complexity measures and also against other meta-learning models, and validate NC’s performance on multiple regression and classification tasks.