Haishan Ye

papers

313

total citations

papers (10)

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

CVPR 2020arXiv

139

citations

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

NEURIPS 2020arXiv

138

citations

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

ICLR 2024arXiv

citations

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

NEURIPS 2023arXiv

citations

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

ICML 2024arXiv

citations

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

ICML 2024

citations

Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence

NEURIPS 2021

citations

Haishan Ye

papers (10)

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

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

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

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?

Decentralized Accelerated Proximal Gradient Descent

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

Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence

papers (10)

MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation

Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

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

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

Can Gaussian Sketching Converge Faster on a Preconditioned Landscape?

Decentralized Accelerated Proximal Gradient Descent

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

Greedy and Random Quasi-Newton Methods with Faster Explicit Superlinear Convergence