Related papers: PaPr: Training-Free One-Step Patch Pruning with Li…
We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error…
Structured pruning is a well-established technique for compressing neural networks, making it suitable for deployment in resource-limited edge devices. This paper presents an efficient Loss-Aware Automatic Selection of Structured Pruning…
Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…
This paper presents an automatic network adaptation method that finds a ConvNet structure well-suited to a given target task, e.g., image classification, for efficiency as well as accuracy in transfer learning. We call the concept…
Neural Network pruning is an increasingly popular way for producing compact and efficient models, suitable for resource-limited environments, while preserving high performance. While the pruning can be performed using a multi-cycle training…
We develop a fast, tractable technique called Net-Trim for simplifying a trained neural network. The method is a convex post-processing module, which prunes (sparsifies) a trained network layer by layer, while preserving the internal…
Deep neural networks (DNNs) are effective in solving many real-world problems. Larger DNN models usually exhibit better quality (e.g., accuracy) but their excessive computation results in long inference time. Model sparsification can reduce…
As deep neural networks (DNNs) are increasingly deployed on edge devices, optimizing models for constrained computational resources is critical. Existing auto-pruning methods face challenges due to the diversity of DNN models, various…
Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g.,…
We present a provable, sampling-based approach for generating compact Convolutional Neural Networks (CNNs) by identifying and removing redundant filters from an over-parameterized network. Our algorithm uses a small batch of input data…
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression…
Convolutional neural networks (CNNs) are typically over-parameterized, bringing considerable computational overhead and memory footprint in inference. Pruning a proportion of unimportant filters is an efficient way to mitigate the inference…
Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this paper, we propose a…
We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…
Pruning the parameters of deep neural networks has generated intense interest due to potential savings in time, memory and energy both during training and at test time. Recent works have identified, through an expensive sequence of training…
Convolutional Neural Networks (CNNs) have demonstrated exceptional performance in recent years. Compressing these models not only reduces storage requirements, making deployment to edge devices feasible, but also accelerates inference,…
Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem as the hyperparameter space for possible network configurations is vast. Here, we…
Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a…
While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a…
Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…