Haishan Ye

5

Papers

18

Total Citations

Papers (5)

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs

Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?