activity
20242026
collaborators

8 papers

cs.LG2026

Convergence Rate Analysis of LION

Yiming Dong, Huan Li, Zhouchen Lin

The LION (evoLved sIgn mOmeNtum) optimizer for deep neural network training was found by Google via program search, with the simple sign update yet showing impressive performance i…

math.OC2026

Convergence Rate Analysis of the AdamW-style Shampoo: Unifying One-Sided and Two-Sided Preconditioning

Huan Li, Yiming Dong, Zhouchen Lin

This paper studies AdamW-style Shampoo, an effective variant of the classical Shampoo that won the external tuning track of the AlgoPerf neural network training competition. Our an…

math.OC2026

Convergence Rate Analysis of SOAP with Arbitrary Orthogonal Projection Matrices

Huan Li, Zhouchen Lin

In this short note, we establish, for the first time, the convergence rate of SOAP, an efficient and popular matrix-based optimizer for training deep neural networks. Our analysis…

cs.LG2025

On the Convergence Rate of AdamW Measured by Norm

Huan Li, Yiming Dong, Zhouchen Lin

As the default optimizer for training large language models, AdamW has achieved remarkable success in deep learning. However, its convergence behavior is not theoretically well-und…

cs.LG2025

Conda: Column-Normalized Adam for Training Large Language Models Faster

Junjie Wang, Pan Zhou, Yiming Dong +6

Large language models (LLMs) have demonstrated impressive generalization and emergent capabilities, yet their pre-training remains computationally expensive and sensitive to optimi…

math.OC2025

On the Convergence Rate of RMSProp and Its Momentum Extension Measured by Norm

Huan Li, Yiming Dong, Zhouchen Lin

Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with…