A unified stochastic convergence theory is developed for adaptive preconditioned first-order methods including AdaGrad variants, Shampoo, and Muon in nonconvex optimization.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Par-S²ZPO matches centralized RLHF sample complexity while converging faster in policy updates and outperforming FedAvg on MuJoCo tasks.
FB-LISA accelerates 3D computed tomography reconstruction by applying a line-search stochastic gradient method with forward-backward splitting on structured mini-batches of full projections.
A solver-in-the-loop method combines a differentiable neural shape prior with a hard-constrained boundary integral equation solver to reconstruct 3D interfaces in EIT while enforcing the governing elliptic PDE at every step.
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.
-
Efficient Federated RLHF via Zeroth-Order Policy Optimization
Par-S²ZPO matches centralized RLHF sample complexity while converging faster in policy updates and outperforming FedAvg on MuJoCo tasks.
-
A Line--Search--Based Stochastic Gradient Method for 3D Computed Tomography
FB-LISA accelerates 3D computed tomography reconstruction by applying a line-search stochastic gradient method with forward-backward splitting on structured mini-batches of full projections.
-
Generative Prior-Guided Neural Interface Reconstruction for 3D Electrical Impedance Tomography
A solver-in-the-loop method combines a differentiable neural shape prior with a hard-constrained boundary integral equation solver to reconstruct 3D interfaces in EIT while enforcing the governing elliptic PDE at every step.