Xiaoyu Wang

Orcid: 0000-0003-4102-4909

Affiliations:
  • Hong Kong University of Science and Technology (HKUST), SAR, Hong Kong, China


According to our database1, Xiaoyu Wang authored at least 12 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

2019
2020
2021
2022
2023
2024
0
1
2
3
4
2
2
1
1
1
1
1
1
2

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Fully First-Order Methods for Decentralized Bilevel Optimization.
CoRR, 2024

ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting.
CoRR, 2024

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Improved Step-Size Schedules for Proximal Noisy Gradient Methods.
IEEE Trans. Signal Process., 2023

On the Convergence of Stochastic Gradient Descent with Bandwidth-based Step Size.
J. Mach. Learn. Res., 2023

Generalized Polyak Step Size for First Order Optimization with Momentum.
Proceedings of the International Conference on Machine Learning, 2023

2022
On Uniform Boundedness Properties of SGD and its Momentum Variants.
CoRR, 2022

Zeroth-Order Randomized Subspace Newton Methods.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
Bandwidth-based Step-Sizes for Non-Convex Stochastic Optimization.
CoRR, 2021

On the Convergence of Step Decay Step-Size for Stochastic Optimization.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Improved Step-Size Schedules for Noisy Gradient Methods.
Proceedings of the IEEE International Conference on Acoustics, 2021

2019
Stochastic proximal quasi-Newton methods for non-convex composite optimization.
Optim. Methods Softw., 2019


  Loading...