activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

A Geometric Characterization of the Stationary Plateau for Two-Layer Neural Networks

Tian Ding, Dawei Li, Ruoyu Sun

We investigate the geometric structure of stationary plateaus that arise in the loss landscape of two-layer neural networks with smooth activation functions. We focus on the phenom…

cs.LG2025

MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning

Yupeng Chen, Senmiao Wang, Yushun Zhang +5

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. Typically, LLMs are first pre-trained on large corpora and subsequently fine-tu…

cs.LG2025

Learning to Gridize: Segment Physical World by Wireless Communication Channel

Juntao Wang, Feng Yin, Tian Ding +3

Gridization, the process of partitioning space into grids where users share similar channel characteristics, serves as a fundamental prerequisite for efficient large-scale network…

cs.LG2025

Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective

Senmiao Wang, Yupeng Chen, Yushun Zhang +2

Graph Neural Networks (GNNs) often suffer from performance degradation as the network depth increases. This paper addresses this issue by introducing initialization methods that en…

cs.LG2025

Adam-mini: Use Fewer Learning Rates To Gain More

Yushun Zhang, Congliang Chen, Ziniu Li +6

We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate…

cs.LG2024

Why Transformers Need Adam: A Hessian Perspective

Yushun Zhang, Congliang Chen, Tian Ding +3

SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Trans…