Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised
a lot of attention currently on post-training pruning (iterative magnitude pruning), and before …

Abstract Low Rank Regularization (LRR), in essence, involves introducing a low rank or
approximately low rank assumption to target we aim to learn, which has achieved great …

Neural net compression can be achieved by approximating each layer's weight matrix by a
low-rank matrix. The real difficulty in doing this is not in training the resulting neural net …

Mixed-precision quantization can potentially achieve the optimal tradeoff between
performance and compression rate of deep neural networks, and thus, have been widely …

To enable DNNs on edge devices like mobile phones, low-rank approximation has been
widely adopted because of its solid theoretical rationale and efficient implementations …

Modern deep neural networks (DNNs) often require high memory consumption and large
computational loads. In order to deploy DNN algorithms efficiently on edge or mobile …

Low-rank compression of a neural network is one of the popular compression techniques,
where it has been known to have two main challenges. The first challenge is determining the …

Filter pruning for a pre-trained convolutional neural network is most normally performed
through human-made constraints or criteria such as norms, ranks, etc. Typically, the pruning …

Abstract Model compression and model defense for deep neural networks (DNNs) have
been extensively and individually studied. Considering the co-importance of model …

Energy efficiency is critical for running computer vision on battery-powered systems, such as
mobile phones or UAVs (unmanned aerial vehicles, or drones). This book collects the …