47 citations · 180 across the 17 of their papers we have counts for
9 papers · 1 filter
Revisiting Sharpness-Aware Minimization: A More Faithful and Effective Implementation
Jianlong Chen, Zhiming Zhou
Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical im…
Recurrent Temporal Revision Graph Networks
Yizhou Chen, Anxiang Zeng, Guangda Huzhang +6
Temporal graphs offer more accurate modeling of many real-world scenarios than static graphs. However, neighbor aggregation, a critical building block of graph networks, for tempor…
Towards Generalized Implementation of Wasserstein Distance in GANs
Minkai Xu, Zhiming Zhou, Guansong Lu +3
Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) duality of Wasserstein distance, is one of the most theoretically sound GAN models. However, in practice it doe…
Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
Yuxuan Song, Lantao Yu, Zhangjie Cao +5
Domain adaptation aims to leverage the supervision signal of source domain to obtain an accurate model for target domain, where the labels are not available. To leverage and adapt…
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?
Tianxing He, Jingzhao Zhang, Zhiming Zhou +1
Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incremental…
Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs
Zhiming Zhou, Jian Shen, Yuxuan Song +2
Lipschitz continuity recently becomes popular in generative adversarial networks (GANs). It was observed that the Lipschitz regularized discriminator leads to improved training sta…
Lipschitz Generative Adversarial Nets
Zhiming Zhou, Jiadong Liang, Yuxuan Song +5
In this paper, we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function…
AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods
Zhiming Zhou, Qingru Zhang, Guansong Lu +3
Adam is shown not being able to converge to the optimal solution in certain cases. Researchers recently propose several algorithms to avoid the issue of non-convergence of Adam, bu…
Activation Maximization Generative Adversarial Nets
Zhiming Zhou, Han Cai, Shu Rong +5
Class labels have been empirically shown useful in improving the sample quality of generative adversarial nets (GANs). In this paper, we mathematically study the properties of the…