Neural Complexity Measures

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.

Authors

• Yoonho Lee
• Juho Lee Kim Jaechul Graduate School of AI, KAIST, Seoul, South Korea
• Sung Ju Hwang
• Eunho Yang Korea Advanced Institute of Science & Technology (KAIST) AITRICS
• Seungjin Choi

Keywords

No keywords are indexed for this paper.