paper-with-me

홈 › Papers

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs

2024-10-31 · Yuchen Yang, Shubham Ugare, Yifan Zhao, Gagandeep Singh, Sasa Misailovic

Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial perturbations, has rarely been addressed in quantization due to unacceptably high cost of certifying robustness. This paper introduces ARQ, an innovative mixed-precision quantization method that not only preserves the clean accuracy of the smoothed classifiers but also maintains their certified robustness. ARQ uses reinforcement learning to find accurate and robust DNN quantization, while efficiently leveraging randomized smoothing, a popular class of statistical DNN verification algorithms. ARQ consistently performs better than multiple state-of-the-art quantization techniques across all the benchmarks and the input perturbation levels. The performance of ARQ quantized networks reaches that of the original DNN with floating-point weights, but with only 1.5% instructions and the highest certified radius. ARQ code is available at https://anonymous.4open.science/r/ARQ-FE4B.

📄 PDF Abstract BibTeX arXiv:2410.24214

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Batch Normalization 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution …
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Inverted Residual Block 설명 없음
Average Pooling 설명 없음

Similar Papers 제목 키워드 기반

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers

2025-11-13 · Minjun Kim, Jaeri Lee, Jongjin Kim, Jeongin Yun 외 arxiv

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degra…

Image ClassificationObject Detection

On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks

2023-09-05 · Wei Huang, Haotong Qin, Yangdong Liu, Jingzhuo Liang 외

Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixture of bit-widths to unleash the accuracy …

Quantization

Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers

2020-08-12 · Manuele Rusci, Marco Fariselli, Alessandro Capotondi, Luca Benini

The severe on-chip memory limitations are currently preventing the deployment of the most accurate Deep Neural Network (DNN) models on tiny MicroController Units (MCUs), even if leveraging an effective 8-bit quantization…

Quantization

Mixed-Precision Quantization: Make the Best Use of Bits Where They Matter Most

2024-12-04 · Yiming Fang, Li Chen, Yunfei Chen, Weidong Wang 외

Mixed-precision quantization offers superior performance to fixed-precision quantization. It has been widely used in signal processing, communication systems, and machine learning. In mixed-precision quantization, bit al…

Quantization

Collaborative Automotive Radar Sensing via Mixed-Precision Distributed Array Completion

2024-03-13 · Arian Eamaz, Farhang Yeganegi, Yunqiao Hu, Mojtaba Soltanalian 외

This paper investigates the effects of coarse quantization with mixed precision on measurements obtained from sparse linear arrays, synthesized by a collaborative automotive radar sensing strategy. The mixed quantization…

Matrix CompletionQuantization