2 citations · 2 across the 9 of their papers we have counts for
11 papers
Weight Decay and Neuron Condensation: A Three-Stage Analysis of Two-Layer ReLU Networks
Cheng Xu, Pengxiao Lin, Zhangchen Zhou +1
Weight decay is widely used as a regularization technique in neural network training, yet its role in neuron condensation (parameter direction alignment) remains unclear. Starting…
CADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents
Junjie Yao, Zhangchen Zhou, Zhi-Qin John Xu
For a long-horizon agent, context is the bottleneck: the history is resent with every request, the window caps task length, and reasoning degrades as the history grows. Replacing s…
Weight-norm Criticality: A Mechanism for Loss Spikes Induced by the Normalization and Weight Decay
Xiaolong Li, Zhangchen Zhou, Zhi-Qin John Xu
Most explanations of training instability focus on \emph{learning-rate criticality}, typically characterized by the Edge of Stability, beyond which optimization becomes unstable. W…
Towards Understanding Adam Convergence on Highly Degenerate Polynomials
Zhiwei Bai, Jiajie Zhao, Zhangchen Zhou +2
Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages remains underexplored. Unlike pri…
Adaptive Preconditioners Trigger Loss Spikes in Adam
Zhiwei Bai, Zhangchen Zhou, Jiajie Zhao +6
Loss spikes commonly emerge during neural network training with the Adam optimizer across diverse architectures and scales, yet their underlying mechanism remains elusive. While pr…
Scalable Complexity Control Facilitates Reasoning Ability of LLMs
Liangkai Hang, Junjie Yao, Zhiwei Bai +17
The reasoning ability of large language models (LLMs) has been rapidly advancing in recent years, attracting interest in more fundamental approaches that can reliably enhance their…
An overview of condensation phenomenon in deep learning
Zhi-Qin John Xu, Yaoyu Zhang, Zhangchen Zhou
In this paper, we provide an overview of a common phenomenon, condensation, observed during the nonlinear training of neural networks: During the nonlinear training of neural netwo…
A rationale from frequency perspective for grokking in training neural network
Zhangchen Zhou, Yaoyu Zhang, Zhi-Qin John Xu
Grokking is the phenomenon where neural networks NNs initially fit the training data and later generalize to the test data during training. In this paper, we empirically provide a…
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism
Zhiwei Wang, Yunji Wang, Zhongwang Zhang +7
Large language models have consistently struggled with complex reasoning tasks, such as mathematical problem-solving. Investigating the internal reasoning mechanisms of these model…
Anchor function: a type of benchmark functions for studying language models
Zhongwang Zhang, Zhiwei Wang, Junjie Yao +4
Understanding transformer-based language models is becoming increasingly crucial, particularly as they play pivotal roles in advancing towards artificial general intelligence. Howe…
Understanding the Initial Condensation of Convolutional Neural Networks
Zhangchen Zhou, Hanxu Zhou, Yuqing Li +1
Previous research has shown that fully-connected networks with small initialization and gradient-based training methods exhibit a phenomenon known as condensation during training.…