Paper泛函梯度下降论文 / Functional GD论文
Functional Gradient Descent with Adaptive Representations
A NeurIPS-accepted paper proposing a method for performing gradient descent directly in function space. It addresses implementation challenges of functional gradient descent through an adaptive representation mechanism and provides theoretical guarantees of convergence to the global minimum.
Timeline (last 90 days)
Sep 28
The paper "Functional Gradient Descent with Adaptive Representations" was accepted at NeurIPS.
Unverified50%