Boao Kong

According to our database, Boao Kong authored at least 10 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization.

Hengrui Zhang, Boao Kong, Engao Zhang, Kun Yuan

CoRR, May, 2026

On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes.

Boao Kong, Hengrui Zhang, Kun Yuan

CoRR, February, 2026

Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization.

Rizhen Hu, Yuan Cao, Boao Kong, Mou Sun, Kun Yuan

CoRR, February, 2026

2025

Row-stochastic matrices can provably outperform doubly stochastic matrices in decentralized learning.

Bing Liu, Boao Kong, Limin Lu, Kun Yuan, Chengcheng Zhao

CoRR, November, 2025

CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure.

Boao Kong, Junzhu Liang, Yuxi Liu, Renjia Deng, Kun Yuan

CoRR, September, 2025

Variable selection of multiple types of data: a PLS approach.

Boao Kong, Huiwen Wang, Shan Lu

Soft Comput., February, 2025

Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity.

Boao Kong, Shuchen Zhu, Songtao Lu, Xinmeng Huang, Kun Yuan

J. Mach. Learn. Res., 2025

D-SOBA: A Single-Loop Decentralized Bilevel Algorithm with Transient Complexity Analysis.

Boao Kong, Shuchen Zhu, Songtao Lu, Xinmeng Huang, Kun Yuan

Proceedings of the 33rd European Signal Processing Conference, 2025

2024

Decentralized Bilevel Optimization over Graphs: Loopless Algorithmic Update and Transient Iteration Complexity.

Boao Kong, Shuchen Zhu, Songtao Lu, Xinmeng Huang, Kun Yuan

CoRR, 2024

SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization.

Shuchen Zhu, Boao Kong, Songtao Lu, Xinmeng Huang, Kun Yuan

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024