CAGE-NAS: Certified Functional Descent for Efficient Model Growth
Read the original on arXiv Machine Learning →CAGE-NAS introduces a method for deciding when to grow a neural network by evaluating an admissibility criterion on approximations of the functional gradient. If the current architecture allows a certified Functional Gradient Descent step, it remains unchanged; otherwise, a function-preserving expansion is performed and re-evaluated. Using a tangent-space-based instance with regularized projection, the approach achieves architectures that rank above the 99.8th percentile in held‑out RMSE among all admissible alternatives within the same parameter budget, without enumerating them during growth.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.