Preprint
Oct 2026
Adaptive Normalized Gradient Method for $(L_0,L_1)$-smooth Problems: Estimating Problem Parameters as a Region
This is the first work to establish, for a single parameter-free algorithm, the best-known iteration-complexity guarantee in the nonconvex setting while also providing the above iteration-complexity guarantee in the convex setting.
Rikiya Okazaki, Shotaro Yagishita, H. Hino
· 0 citations