Deyi Liu

Orcid: 0000-0002-3321-2232

According to our database1, Deyi Liu authored at least 14 papers between 2020 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
SPARKLING: Balancing Signal Preservation and Symmetry Breaking for Width-Progressive Learning.
CoRR, February, 2026

2025
GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models.
CoRR, October, 2025

Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning Models.
CoRR, September, 2025

Model Merging in Pre-training of Large Language Models.
CoRR, May, 2025

2023
A new randomized primal-dual algorithm for convex optimization with fast last iterate convergence rates.
Optim. Methods Softw., January, 2023

2022
Efficient and Provable Algorithms for Convex Optimization Problems Beyond Lipschitz Continuous Gradients.
PhD thesis, 2022

New Primal-Dual Algorithms for a Class of Nonsmooth and Nonlinear Convex-Concave Minimax Problems.
SIAM J. Optim., 2022

A Newton Frank-Wolfe method for constrained self-concordant minimization.
J. Glob. Optim., 2022

An application of an automation operation and maintenance tool design and application.
Proceedings of the 4th International Conference on Robotics, 2022

2021
Robust and Generalizable Visual Representation Learning via Random Convolutions.
Proceedings of the 9th International Conference on Learning Representations, 2021

Monitoring Method for Archival Data Change of Electrical Information Acquisition System Based On Data Middle Office and Its Application.
Proceedings of the AIAM 2021: 3rd International Conference on Artificial Intelligence and Advanced Manufacture, Manchester, United Kingdom, October 23, 2021

2020
An Inexact Interior-Point Lagrangian Decomposition Algorithm with Inexact Oracles.
J. Optim. Theory Appl., 2020

Robust and Generalizable Visual Representation Learning via Random Convolutions.
CoRR, 2020

Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear Function.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020


  Loading...