相关论文: Pruning as Regularization: Sensitivity-Aware One-S…

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain…

Neural networks can be drastically shrunk in size by removing redundant parameters. While crucial for the deployment on resource-constraint hardware, oftentimes, compression comes with a severe drop in accuracy and lack of adversarial…

Self-supervised learning (SSL) models such as WavLM have substantially advanced speaker diarization by providing rich contextual speech representations. However, the high computational and memory costs of these models hinder deployment in…

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

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,…

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three…

The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model…

Adaptive network pruning approach has recently drawn significant attention due to its excellent capability to identify the importance and redundancy of layers and filters and customize a suitable pruning solution. However, it remains…

Towards fast, hardware-efficient, and low-complexity receivers, we propose a compression-aware learning approach and examine it on free-space optical (FSO) receivers for turbulence mitigation. The learning approach jointly quantize, prune,…

Deep learning harnesses massive parallel floating-point processing to train and evaluate large neural networks. Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than…

An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are…

To address the enormous size of Large Language Models (LLMs), model compression methods, such as quantization and pruning, are often deployed, especially on edge devices. In this work, we focus on layer-wise post-training quantization and…

Sharpness-Aware Minimization (SAM) has recently emerged as an effective technique for improving DNN robustness to input variations. However, its interplay with the compactness requirements of on-device DNN deployments remains less explored.…

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.…

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

As Deep Neural Networks (DNNs) usually are overparameterized and have millions of weight parameters, it is challenging to deploy these large DNN models on resource-constrained hardware platforms, e.g., smartphones. Numerous network…

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

We introduce a method to speed up training by 2x and inference by 3x in deep neural networks using structured pruning applied before training. Unlike previous works on pruning before training which prune individual weights, our work…

Encoding input coordinates with sinusoidal functions into multilayer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of low-dimensional signals, enabling the modeling of high-frequency details. However,…