Theory-Inspired Path-Regularized Differential Network Architecture Search
–Neural Information Processing Systems
Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g.
Neural Information Processing Systems
Jan-24-2025, 20:31:29 GMT