Adam-HNAG is a splitting-based reformulation of Adam that yields the first convergence proof for Adam-type methods, including accelerated rates, in convex smooth optimization.
First order optimization methods based on hessian-driven nesterov accelerated gradient flow, 2019
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
math.OC 4years
2026 4verdicts
UNVERDICTED 4roles
method 1polarities
use method 1representative citing papers
Acc-Sinkhorn achieves O(1/k²) convergence for entropy-regularized OT via Hessian-driven Nesterov acceleration on a reduced dual objective, improving unregularized OT approximation to Õ(n²/ε) complexity.
SHANG++ delivers faster convergence and stronger robustness to multiplicative noise in stochastic optimization for both convex and strongly convex problems, with explicit parameters and competitive deep-learning results.
AAMD combines preconditioning, acceleration, and adaptivity in mirror descent using a Lyapunov budget to achieve O(1/k^2) rates under dual relative smoothness and bounded sublevel sets.
citing papers explorer
-
Adam-HNAG: A Convergent Reformulation of Adam with Accelerated Rate
Adam-HNAG is a splitting-based reformulation of Adam that yields the first convergence proof for Adam-type methods, including accelerated rates, in convex smooth optimization.
-
Accelerating Sinkhorn for Entropy-Regularized Optimal Transport
Acc-Sinkhorn achieves O(1/k²) convergence for entropy-regularized OT via Hessian-driven Nesterov acceleration on a reduced dual objective, improving unregularized OT approximation to Õ(n²/ε) complexity.
-
SHANG++: Robust Stochastic Acceleration under Multiplicative Noise
SHANG++ delivers faster convergence and stronger robustness to multiplicative noise in stochastic optimization for both convex and strongly convex problems, with explicit parameters and competitive deep-learning results.
-
Adaptive Accelerated Mirror Descent in Primal and Dual Spaces
AAMD combines preconditioning, acceleration, and adaptivity in mirror descent using a Lyapunov budget to achieve O(1/k^2) rates under dual relative smoothness and bounded sublevel sets.