4 citations · 10 across the 7 of their papers we have counts for
4 papers · 1 filter
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
Zixiang Chen, Huizhuo Yuan, Yongqian Li +3
Discrete diffusion models have emerged as powerful tools for high-quality data generation. Despite their success in discrete spaces, such as text generation tasks, the acceleration…
Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
Yiwen Kou, Zixiang Chen, Quanquan Gu
The implicit bias towards solutions with favorable properties is believed to be a key reason why neural networks trained by gradient-based optimization can generalize well. While t…
Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
Zixiang Chen, Junkai Zhang, Yiwen Kou +3
The challenge of overfitting, in which the model memorizes the training data and fails to generalize to test data, has become increasingly significant in the training of large neur…
Benign Overfitting for Two-layer ReLU Convolutional Neural Networks
Yiwen Kou, Zixiang Chen, Yuanzhou Chen +1
Modern deep learning models with great expressive power can be trained to overfit the training data but still generalize well. This phenomenon is referred to as \textit{benign over…