13 citations · 25 across the 7 of their papers we have counts for
5 papers · 1 filter
Perceptual Generative Autoencoders
Zijun Zhang, Ruixiang Zhang, Zongpeng Li +2
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dim…
Removing the Feature Correlation Effect of Multiplicative Noise
Zijun Zhang, Yining Zhang, Zongpeng Li
Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an…
A Block-wise, Asynchronous and Distributed ADMM Algorithm for General Form Consensus Optimization
Rui Zhu, Di Niu, Zongpeng Li
Many machine learning models, including those with non-smooth regularizers, can be formulated as consensus optimization problems, which can be solved by the alternating direction m…
Asynchronous Stochastic Proximal Methods for Nonconvex Nonsmooth Optimization
Rui Zhu, Di Niu, Zongpeng Li
We study stochastic algorithms for solving nonconvex optimization problems with a convex yet possibly nonsmooth regularizer, which find wide applications in many practical machine…
Normalized Direction-preserving Adam
Zijun Zhang, Lin Ma, Zongpeng Li +1
Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent stu…