相关论文: Scalable iterative pruning of large language and v…

This paper describes a channel-selection approach for simplifying deep neural networks. Specifically, we propose a new type of generic network layer, called pruning layer, to seamlessly augment a given pre-trained model for compression.…

In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be…

The learning capability of a neural network improves with increasing depth at higher computational costs. Wider layers with dense kernel connectivity patterns furhter increase this cost and may hinder real-time inference. We propose feature…

Large Language Models (LLMs) have achieved remarkable success in various natural language processing tasks, including language modeling, understanding, and generation. However, the increased memory and computational costs associated with…

Over the past decade, the use of machine learning has increased exponentially. Models are far more complex than ever before, growing to gargantuan sizes and housing millions of weights. Unfortunately, the fact that large models have become…

Oftentimes, machine learning applications using neural networks involve solving discrete optimization problems, such as in pruning, parameter-isolation-based continual learning and training of binary networks. Still, these discrete problems…

Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform. Consequently, they can often be compressed using techniques such…

Structured pruning is a practical approach to deploying large language models (LLMs) efficiently, as it yields compact, hardware-friendly architectures. However, the dominant local paradigm is task-agnostic: by optimizing layer-wise…

Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for training and inference. However, current methods are…

Despite exceptional capabilities, Large Language Models (LLMs) still face deployment challenges due to their enormous size. Post-training structured pruning is a promising solution that prunes LLMs without the need for retraining, reducing…

Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…

Pruning and quantization techniques have been broadly successful in reducing the number of parameters needed for large neural networks, yet theoretical justification for their empirical success falls short. We consider a randomized greedy…

Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, removing some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda, either concentrated…

Recurrent neural networks (RNNs) have been widely adopted in temporal sequence analysis, where realtime performance is often in demand. However, RNNs suffer from heavy computational workload as the model often comes with large weight…

The remarkable performance of large language models (LLMs) in various language tasks has attracted considerable attention. However, the ever-increasing size of these models presents growing challenges for deployment and inference.…

Deep neural networks have usually to be compressed and accelerated for their usage in low-power, e.g. mobile, devices. Recently, massively-parallel hardware accelerators were developed that offer high throughput and low latency at low power…

Structured pruning reduces the computational overhead of deep neural networks by removing redundant sub-structures. However, assessing the relative importance of different sub-structures remains a significant challenge, particularly in…

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks and cascaded…

Large language models (LLMs) have achieved remarkable progress in natural language processing, but their high computational and memory costs hinder deployment on resource-constrained devices. Binarization represents the most extreme form of…

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance…