661 citations · 1.6k across the 26 of their papers we have counts for
7 papers · 1 filter
Neural Predictor for Neural Architecture Search
Wei Wen, Hanxiao Liu, Hai Li +3
Neural Architecture Search methods are effective but often use complex algorithms to come up with the best architecture. We propose an approach with three basic steps that is conce…
Trained Rank Pruning for Efficient Deep Neural Networks
Yuhui Xu, Yuxi Li, Shuai Zhang +7
To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attemp…
Conditional Transferring Features: Scaling GANs to Thousands of Classes with 30% Less High-quality Data for Training
Chunpeng Wu, Wei Wen, Yiran Chen +1
Generative adversarial network (GAN) has greatly improved the quality of unsupervised image generation. Previous GAN-based methods often require a large amount of high-quality trai…
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
Huanrui Yang, Wei Wen, Hai Li
In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0…
Joint Regularization on Activations and Weights for Efficient Neural Network Pruning
Qing Yang, Wei Wen, Zuoguan Wang +1
With the rapid scaling up of deep neural networks (DNNs), extensive research studies on network model compression such as weight pruning have been performed for improving deploymen…
AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
Wei Wen, Feng Yan, Yiran Chen +1
Depth is a key component of Deep Neural Networks (DNNs), however, designing depth is heuristic and requires many human efforts. We propose AutoGrow to automate depth discovery in D…
PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
Sangkug Lym, Esha Choukse, Siavash Zangeneh +3
State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resourc…