A unified stochastic convergence theory is developed for adaptive preconditioned first-order methods including AdaGrad variants, Shampoo, and Muon in nonconvex optimization.
WNGrad: Lear n the learning rate in gradient descent
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces bAdag, an AdaGrad-based block coordinate gradient method with ergodic sublinear convergence proofs for smooth nonconvex objectives under block Lipschitz gradient assumptions, covering cyclic, uniform random, and Gauss-Southwell selection plus box constraints.
citing papers explorer
-
A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad, Shampoo and Muo
A unified stochastic convergence theory is developed for adaptive preconditioned first-order methods including AdaGrad variants, Shampoo, and Muon in nonconvex optimization.
-
bAdag: an adaptive block coordinate gradient method for smooth nonconvex functions
Introduces bAdag, an AdaGrad-based block coordinate gradient method with ergodic sublinear convergence proofs for smooth nonconvex objectives under block Lipschitz gradient assumptions, covering cyclic, uniform random, and Gauss-Southwell selection plus box constraints.