Profiles2020-2026
Feihu Huang
Nanjing University of Aeronautics and Astronautics
18Papers
1Last author
7Unique co-authors
9First author
1Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers18
- LiMuon: Light and Fast Muon Optimizer for Large ModelsAuthor 1 of 3ICML 2026 · 20 citations
- Faster Double Adaptive Gradient MethodsAuthor 1 of 2AAAI 2025
- Generalized Smooth Bilevel Optimization with Nonconvex Lower-LevelAuthor 3 of 3ICML 2025
- Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel OptimizationAuthor 1 of 1ICML 2024 · 14 citations
- Faster Adaptive Decentralized Learning AlgorithmsAuthor 1 of 2ICML 2024 · 4 citations
- FedDA: Faster Adaptive Gradient Methods for Federated Constrained OptimizationAuthor 2 of 3ICLR 2024 · 2 citations
- Faster Adaptive Federated LearningAuthor 2 of 4AAAI 2023 · 99 citations
- Structural Alignment for Network Pruning through Partial RegularizationAuthor 4 of 5ICCV 2023 · 26 citations
- Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level ProblemsAuthor 2 of 3NeurIPS 2023 · 4 citations
- Enhanced Bilevel Optimization via Bregman DistanceAuthor 1 of 4NeurIPS 2022 · 41 citations
- Bregman Gradient Policy OptimizationAuthor 1 of 3ICLR 2022 · 19 citations
- A Faster Decentralized Algorithm for Nonconvex Minimax ProblemsAuthor 2 of 4NeurIPS 2021 · 72 citations
- SUPER-ADAM: Faster and Universal Framework of Adaptive GradientsAuthor 1 of 3NeurIPS 2021 · 55 citations
- Efficient Mirror Descent Ascent Methods for Nonsmooth Minimax ProblemsAuthor 1 of 3NeurIPS 2021 · 46 citations
- Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed LearningAuthor 2 of 3AAAI 2021 · 17 citations
- Optimal Underdamped Langevin MCMC MethodAuthor 2 of 3NeurIPS 2021 · 5 citations
- Network Pruning via Performance MaximizationAuthor 2 of 4CVPR 2021
- Momentum-Based Policy Gradient MethodsAuthor 1 of 4ICML 2020 · 47 citations
