Yangchuan Wang

2 accepted papers

2026

Generative Branching for Mixed-Integer Linear Programming

Ruobing Wang, Xin Li, Yangchuan Wang, Zijian Zhang, Mingzhong Wang

AAAI 2026technical

Branch-and-bound (B&B) is a fundamental algorithmic framework for solving Mixed-Integer Linear Programming (MILP) problems, where branching decisions critically affect solver efficiency. Recent learning-based methods apply imitation learning to select branching variables, but their deterministic pre

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

AdaR: An Adaptive Gradient Method with Cyclical Restarting of Moment Estimations

Yangchuan Wang, Lianhong Ding, Peng Shi

IJCAI 2025

Adaptive gradient methods, primarily based on Adam, are prevalent in training neural networks, adjusting step sizes via exponentially decaying averages of gradients and squared gradients. Adam assigns small weights to distant gradients, termed long-tail gradients in this paper. However, these gradie

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗