collaborators

5 papers

cs.LG2026

Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks

Wenquan Ma, Yang Sui, Jiaye Teng +3

Algorithmic stability is among the most potent techniques in generalization analysis. However, its derivation usually requires a stepsize under non-convex…

cs.LG2025

BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training

Wenjie Zhou, Bohan Wang, Wei Chen +1

Recent studies \citep{gur2018gradient,song2024does, wen2024understanding} highlight a fundamental dichotomy in deep learning optimization: Although parameter updates along the top…

cs.LG2025

Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space

Mingyang Yi, Bohan Wang

Recently, optimization on the Riemannian manifold have provided valuable insights to the optimization community. In this regard, extending these methods to to the Wasserstein space…

cs.AI2025

Solving Formal Math Problems by Decomposition and Iterative Reflection

Yichi Zhou, Jianqiu Zhao, Yongxin Zhang +14

General-purpose Large Language Models (LLMs) have achieved remarkable success in intelligence, performing comparably to human experts on complex reasoning tasks such as coding and…

cs.LG2025

AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training

Huishuai Zhang, Bohan Wang, Luoxin Chen

We introduce AdamS, a simple yet effective alternative to Adam for large language model (LLM) pretraining and post-training. By leveraging a novel denominator, i.e., the root of we…