AI RESEARCH
SHANG++: Robust Stochastic Acceleration under Multiplicative Noise
arXiv CS.LG
•
ArXi:2603.09355v1 Announce Type: cross Under the multiplicative noise scaling (MNS) condition, original Nestero acceleration is provably sensitive to noise and may diverge when gradient noise overwhelms the signal. In this paper, we develop two accelerated stochastic gradient descent methods by discretizing the Hessian-driven Nestero accelerated gradient flow. We first derive SHANG, a direct Gauss-Seidel-type discretization that already improves stability under MNS. We then