相关论文: Improving Neural Network Quantization without Retr…

Quantization for deep neural networks (DNNs) is the process of mapping the parameter values of DNNs from original data types to other data types of lower precision to reduce model sizes and make inference faster. Quantization often maps…

Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often…

While 4-bit quantization is essential for high-throughput deployment of Large Language Models, activation outliers often lead to significant accuracy degradation due to the restricted dynamic range of low-bit formats. In this paper, we…

Post-training quantization~(PTQ) of transformer language models faces significant challenges due to the existence of detrimental outliers in activations. We observe that these outliers are concentrated in specific channels and are…

Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and inference, a structural re-parameterized…

Network quantization has emerged as one of the most practical model compression techniques, which significantly reduces a model's memory and compute consumption by mapping floating-point numbers to low-bit representations. However, existing…

Transformer models have been widely adopted in various domains over the last years, and especially large language models have advanced the field of AI significantly. Due to their size, the capability of these networks has increased…

Outlier Features (OFs) are neurons whose activation magnitudes significantly exceed the average over a neural network's (NN) width. They are well known to emerge during standard transformer training and have the undesirable effect of…

Quantization techniques, including quantization-aware training (QAT) and post-training quantization (PTQ), have become essential for inference acceleration of image super-resolution (SR) networks. Compared to QAT, PTQ has garnered…

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from…

Diffusion models have achieved remarkable success in image generation but come with significant computational costs, posing challenges for deployment in resource-constrained environments. Recent post-training quantization (PTQ) methods have…

Convolutional Neural Networks (CNNs) have shown to be powerful medical image segmentation models. In this study, we address some of the main unresolved issues regarding these models. Specifically, training of these models on small medical…

Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse…

Out-of-distribution (OOD) detection and OOD generalization are widely studied in Deep Neural Networks (DNNs), yet their relationship remains poorly understood. We empirically show that the degree of Neural Collapse (NC) in a network layer…

Optimal transmission switching (OTS) improves optimal power flow (OPF) by selectively opening transmission lines, but its mixed-integer formulation increases computational complexity, especially on large grids. To address this, we propose a…

We consider the problem of accurate quantization for language models, where both the weights and activations are uniformly quantized to 4 bits per parameter, the lowest bitwidth format natively supported by GPU hardware. In this context,…

This paper aims at rapid deployment of the state-of-the-art deep neural networks (DNNs) to energy efficient accelerators without time-consuming fine tuning or the availability of the full datasets. Converting DNNs in full precision to…

In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks.…

The use of machine learning methods to tackle challenging physical layer signal processing tasks has attracted significant attention. In this work, we focus on the use of neural networks (NNs) to perform pilot-assisted channel estimation in…

The accuracy of machine learning interatomic potentials suffers from reference data that contains numerical noise. Often originating from unconverged or inconsistent electronic-structure calculations, this noise is challenging to identify.…