5 citations · 8 across the 3 of their papers we have counts for
3 papers
cs.LG2024
Learning Hierarchical Polynomials of Multiple Nonlinear Features with Three-Layer Networks
Hengyu Fu, Zihao Wang, Eshaan Nichani +1
In deep learning theory, a critical question is to understand how neural networks learn hierarchical features. In this work, we study the learning of hierarchical polynomials of \t…
cs.LG2024★ 5 cited
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory
Hengyu Fu, Zhuoran Yang, Mengdi Wang +1
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. In th…
cs.LG2023★ 3 cited
What can a Single Attention Layer Learn? A Study Through the Random Features Lens
Hengyu Fu, Tianyu Guo, Yu Bai +1
Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs…