Parameter-free version of Adaptive Gradient Methods for Strongly-Convex Functions
Theorem: Suppose all loss functions are
Proof:
Step 1:
Step 2: find
Note that
The algorithm has a hyperparameter
Full paper on arXiv.
Theorem: Suppose all loss functions are
Proof:
Step 1:
Step 2: find
Note that
The algorithm has a hyperparameter
Full paper on arXiv.