相关论文: Nonuniform-to-Uniform Quantization: Towards Accura…

Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable accuracy for INT8 (or…

With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying…

Huge computational costs brought by convolution and batch normalization (BN) have caused great challenges for the online training and corresponding applications of deep neural networks (DNNs), especially in resource-limited devices.…

Quantization is commonly used in Deep Neural Networks (DNNs) to reduce the storage and computational complexity by decreasing the arithmetical precision of activations and weights, a.k.a. tensors. Efficient hardware architectures employ…

Deep neural networks with lower precision weights and operations at inference time have advantages in terms of the cost of memory space and accelerator power. The main challenge associated with the quantization algorithm is maintaining…

Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision. Quantization reduces model size and inference…

Uncertainty quantification (UQ) has increasing importance in building robust high-performance and generalizable materials property prediction models. It can also be used in active learning to train better models by focusing on getting new…

Quantum state tomography (QST) aiming at reconstructing the density matrix of a quantum state plays an important role in various emerging quantum technologies. Recognizing the challenges posed by imperfect measurement data, we develop a…

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…

Neural network quantization is an effective way to compress deep models and improve their execution latency and energy efficiency, so that they can be deployed on mobile or embedded devices. Existing quantization methods require original…

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas…

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on terminal medical…

Quantization has been proven to be an effective method for reducing the computing and/or storage cost of DNNs. However, the trade-off between the quantization bitwidth and final accuracy is complex and non-convex, which makes it difficult…

We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. To…

Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ)…

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Neural network quantization procedure is the necessary step for porting of neural networks to mobile devices. Quantization allows accelerating the inference, reducing memory consumption and model size. It can be performed without…

At present, the quantification methods of neural network models are mainly divided into post-training quantization (PTQ) and quantization aware training (QAT). Post-training quantization only need a small part of the data to complete the…

The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available…

Performing unsupervised domain adaptation on resource-constrained edge devices is challenging. Existing research typically adopts architecture optimization (e.g., designing slimmable networks) but requires expensive training costs.…