Neural Complexity Measures
This work addresses the problem of designing effective complexity measures for deep learning practitioners, but it appears incremental as it builds on existing meta-learning approaches.
The authors tackled the challenge of predicting and explaining generalization in deep neural networks by proposing Neural Complexity (NC), a meta-learning framework that learns a scalar complexity measure from heterogeneous tasks, and they validated its performance on multiple regression and classification tasks.
While various complexity measures for deep neural networks exist, specifying an appropriate measure capable of predicting and explaining generalization in deep networks has proven challenging. We propose Neural Complexity (NC), a meta-learning framework for predicting generalization. Our model learns a scalar complexity measure through interactions with many heterogeneous tasks in a data-driven way. The trained NC model can be added to the standard training loss to regularize any task learner in a standard supervised learning scenario. We contrast NC's approach against existing manually-designed complexity measures and other meta-learning models, and we validate NC's performance on multiple regression and classification tasks