2 papers
cs.LG2024
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK
Hongru Yang, Ziyu Jiang, Ruizhe Zhang +2
We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime, where the networks' biases are initialized to some constant rather than zero. We prove t…
cs.LG2024
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Hongru Yang, Bhavya Kailkhura, Zhangyang Wang +1
Understanding the training dynamics of transformers is important to explain the impressive capabilities behind large language models. In this work, we study the dynamics of trainin…