Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to improve the overall performance. However, it is challenging to find the optimal bitwidth (i.e., precision) for weights and activations of each layer efficiently. Meanwhile, it is yet unclear how to perform convolution for weights and activations of different precision efficiently on generic hardware platforms. To resolve these two issues, in this paper, we first propose an Efficient Bitwidth Search (EBS) algorithm, which reuses the meta weights for different quantization bitwidth and thus the strength for each candidate precision can be optimized directly w.r.t the objective without superfluous copies, reducing both the memory and computational cost significantly. Second, we propose a binary decomposition algorithm that converts weights and activations of different precision into binary matrices to make the mixed precision convolution efficient and practical. Experiment results on CIFAR10 and ImageNet datasets demonstrate our mixed precision QNN outperforms the handcrafted uniform bitwidth counterparts and other mixed precision techniques.
Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with homogeneous bitwidth for the same size constraint. Since choosing the optimal bitwidths is not straight forward, training methods, which can learn them, are desirable. Differentiable quantization with straight-through gradients allows to learn the quantizer's parameters using gradient methods. We show that a suited parametrization of the quantizer is the key to…
Hong Kong University of Science and Technology（香港科技大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Jockey Club Institute for Advanced Study, HKUST（香港科技大学赛马会高等研究院）；Reality Labs, Meta Inc（Meta公司现实实验室）；ACCESS - AI Chip Center for Emerging Smart Systems（新兴智能系统AI芯片中心（ACCESS））；Carnegie Mellon University（卡内基梅隆大学）
In order to deploy deep models in a computationally efficient manner, model quantization approaches have been frequently used. In addition, as new hardware that supports mixed bitwidth arithmetic operations, recent research on mixed precision quantization (MPQ) begins to fully leverage the capacity of representation by searching optimized bitwidths for different layers and modules in a network. However, previous studies mainly search the MPQ strategy in a costly scheme using reinforcement learning, neural architecture search, etc., or simply utilize partial prior knowledge for bitwidth assignm…
Carnegie Mellon University（卡内基梅隆大学）；Facebook Inc.（Facebook公司）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
Weight quantization for deep ConvNets has shown promising results for applications such as image classification and semantic segmentation and is especially important for applications where memory storage is limited. However, when aiming for quantization without accuracy degradation, different tasks may end up with different bitwidths. This creates complexity for software and hardware support and the complexity accumulates when one considers mixed-precision quantization, in which case each layer's weights use a different bitwidth. Our key insight is that optimizing for the least bitwidth subjec…
Fully quantized training (FQT), which uses low-bitwidth hardware by quantizing the activations, weights, and gradients of a neural network model, is a promising approach to accelerate the training of deep neural networks. One major challenge with FQT is the lack of theoretical understanding, in particular of how gradient quantization impacts convergence properties. In this paper, we address this problem by presenting a statistical framework for analyzing FQT algorithms. We view the quantized gradient of FQT as a stochastic estimator of its full precision counterpart, a procedure known as quant…
Deep quantization of neural networks (below eight bits) offers significant promise in reducing their compute and storage cost. Albeit alluring, without special techniques for training and optimization, deep quantization results in significant accuracy loss. To further mitigate this loss, we propose a novel sinusoidal regularization, called SinReQ1, for deep quantized training. SinReQ adds a periodic term to the original objective function of the underlying training algorithm. SinReQ exploits the periodicity, differentiability, and the desired convexity profile in sinusoidal functions to automa…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；AITRICS
In practical federated learning scenarios, the participating devices may have different bitwidths for computation and memory storage by design. However, despite the progress made in device-heterogeneous federated learning scenarios, the heterogeneity in the bitwidth specifications in the hardware has been mostly overlooked. We introduce a pragmatic FL scenario with bitwidth heterogeneity across the participating devices, dubbed as Bitwidth Heterogeneous Federated Learning (BHFL). BHFL brings in a new challenge, that the aggregation of model parameters with different bitwidths could result in s…
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 receive customer models without training data. Specialized hardware for handling activation outliers can enable low-precision neural networks, but at the cost of nontrivial area overhead. We instead propose overwrite quantization (OverQ), a lightweight hardware technique that opportunistically increases bitwidth for activation outliers by overwriting nearby zeros…
Meta Reality Lab Research（Meta现实实验室研究部门）；AGH UST（AGH科技大学）
Deploying Deep Neural Networks in low-power embedded devices for real time-constrained applications requires optimization of memory and computational complexity of the networks, usually by quantizing the weights. Most of the existing works employ linear quantization which causes considerable degradation in accuracy for weight bit widths lower than 8. Since the distribution of weights is usually non-uniform (with most weights concentrated around zero), other methods, such as logarithmic quantization, are more suitable as they are able to preserve the shape of the weight distribution more precis…
We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a neural network into individual bitlayers and accumulates them using fast 1-bit operations while maintaining activations in full precision. PrecisionBatching not only facilitates quantized inference at low bitwidths (< 8 bits) without the need for retraining/recalibration, but also 1) enables traditional hardware platforms the ability to realize inference speedups…
This paper proposes CodeX, an end-to-end framework that facilitates encoding, bitwidth customization, fine-tuning, and implementation of neural networks on FPGA platforms. CodeX incorporates nonlinear encoding to the computation flow of neural networks to save memory. The encoded features demand significantly lower storage compared to the raw full-precision activation values; therefore, the execution flow of CodeX hardware engine is completely performed within the FPGA using on-chip streaming buffers with no access to the off-chip DRAM. We further propose a fully-automated algorithm inspired b…
ETH Zurich（苏黎世联邦理工学院）；Singapore Management University（新加坡管理大学）
We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on low-resource mobile and embedded platforms. We propose Adaptive Loss-aware Quantization (ALQ), a new MBN quantization pipeline that is able to achieve an average bitwidth below one-bit without notable loss in inference accuracy. Unlike previous MBN quantization solutions that train a quantizer by minimizing the error to reconstruct full precision weights, ALQ…
Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a trained model to low-bitwidth integer values using scale factors. Excessive quantization, reducing precision too aggressively, results in accuracy degradation. When scale factors are shared at a coarse granularity across many dimensions of each tensor, effective precision of individual elements within the tensor are limited. To reduce quantization-related accuracy loss, we propos…
Universita’ di Bologna（博洛尼亚大学）；ETH Zurich（苏黎世联邦理工学院）
This paper presents a novel end-to-end methodology for enabling the deployment of low-error deep networks on microcontrollers. To fit the memory and computational limitations of resource-constrained edge-devices, we exploit mixed low-bitwidth compression, featuring 8, 4 or 2-bit uniform quantization, and we model the inference graph with integer-only operations. Our approach aims at determining the minimum bit precision of every activation and weight tensor given the memory constraints of a device. This is achieved through a rule-based iterative procedure, which cuts the number of bits of the …
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for each layer: it requires domain experts to explore the vast design space trading off among accuracy, latency, energy, and model size, which is both time-consuming and sub-optimal. Conventional quantization algorithm ignores the different hardware architectures and quantizes all the layers in a unifor…
Zhejiang University（浙江大学）；China Research and Development Academy of Machinery Equipment（中国机械科学研究总院集团有限公司）
The quantized neural networks (QNNs) can be useful for neural network acceleration and compression, but during the training process they pose a challenge: how to propagate the gradient of loss function through the graph flow with a derivative of 0 almost everywhere. In response to this non-differentiable situation, we propose a novel Asymptotic-Quantized Estimator (AQE) to estimate the gradient. In particular, during back-propagation, the graph that relates inputs to output remains smoothness and differentiability. At the end of training, the weights and activations have been quantized to low-…
The Chinese University of Hong Kong（香港中文大学）；SenseBrain, Ltd（SenseBrain有限公司）；Shanghai AI Lab（上海人工智能实验室）；The University of Hong Kong（香港大学）
Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune these values, we present a fully differentiable approach to learn all of them, named Differentiable Dynamic Quantization (DDQ), which has several benefits. (1) DDQ is able to quantize challenging lightweight architectures like MobileNets, where different layers prefer different quantization parameters. (2) DDQ is hardware-friendly and can be easily implement…
Applications of neural networks on edge systems have proliferated in recent years but the ever-increasing model size makes neural networks not able to deploy on resource-constrained microcontrollers efficiently. We propose bit-serial weight pools, an end-to-end framework that includes network compression and acceleration of arbitrary sub-byte precision. The framework can achieve up to 8x compression compared to 8-bit networks by sharing a pool of weights across the entire network. We further propose a bit-serial lookup based software implementation that allows runtime-bitwidth tradeoff and is …
Department of Precision Instrument（精密仪器系）；Department of Automation（自动化系）；Center for Brain Inspired Computing Research（脑启发计算研究中心）；Beijing Innovation Center for Future Chip（北京未来芯片创新中心）；Tsinghua University（清华大学）
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics. Although previous works have successfully reduced precision in inference, transferring both training and inference processes to low-bitwidth integers has not been demonstrated simultaneously. In this work, we develop a new method termed as "WAGE" to discretize both training and inference, where weights (W), activations (A), gradients (G) and errors (E) among layers are shifted and linearly constrained to low-bitwidth integers. To perform pure discrete data…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Brain（谷歌大脑）
We consider the post-training quantization problem, which discretizes the weights of pre-trained deep neural networks without re-training the model. We propose multipoint quantization, a quantization method that approximates a full-precision weight vector using a linear combination of multiple vectors of low-bit numbers; this is in contrast to typical quantization methods that approximate each weight using a single low precision number. Computationally, we construct the multipoint quantization with an efficient greedy selection procedure, and adaptively decides the number of low precision poin…
Eindhoven University of Technology（埃因霍温理工大学）；Philips Innovation Services（飞利浦创新服务）
Convolutional Neural Networks (CNNs) have proven to be a powerful state-of-the-art method for image classification tasks. One drawback however is the high computational complexity and high memory consumption of CNNs which makes them unfeasible for execution on embedded platforms which are constrained on physical resources needed to support CNNs. Quantization has often been used to efficiently optimize CNNs for memory and computational complexity at the cost of a loss of prediction accuracy. We therefore propose a method to optimally quantize the weights, biases and activations of each layer of…
LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits
Dept. Computing Science & Alberta Machine Intelligence Institute (Amii), University of Alberta（计算科学系及阿尔伯塔人工智能研究所（Amii），阿尔伯塔大学）；RBC Borealis；Canada CIFAR AI Chair（加拿大CIFAR人工智能 chair）
Recent work in network quantization produced state-of-the-art results using mixed precision quantization. An imperative requirement for many efficient edge device hardware implementations is that their quantizers are uniform and with power-of-two thresholds. In this work, we introduce the Hardware Friendly Mixed Precision Quantization Block (HMQ) in order to meet this requirement. The HMQ is a mixed precision quantization block that repurposes the Gumbel-Softmax estimator into a smooth estimator of a pair of quantization parameters, namely, bit-width and threshold. HMQs use this to search over…
SenseTime Research（商汤科技研究院）；Peking University（北京大学）；University of Science and Technology Beijing（北京科技大学）
Emergent hardwares can support mixed precision CNN models inference that assign different bitwidths for different layers. Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations. In this paper, we propose a novel soft Barrier Penalty based NAS (BP-NAS) for mixed precision quantization, which ensures all the searched models are inside the valid domain defined by the complexity …
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；IST Austria（奥地利科学技术研究所）；Neural Magic, Inc.（Neural Magic公司）
University of Notre Dame（圣母大学）；Google LLC（谷歌有限责任公司）
Serving large-scale machine learning (ML) models efficiently and with low latency has become challenging owing to increasing model size and complexity. Quantizing models can simultaneously reduce memory and compute requirements, facilitating their widespread access. However, for large models not all layers are equally amenable to the same numerical precision and aggressive quantization can lead to unacceptable loss in model accuracy. One approach to prevent this accuracy degradation is mixed-precision quantization, which allows different tensors to be quantized to varying levels of numerical p…
University of California, Irvine（加州大学欧文分校）；Rain Neuromorphics Inc（Rain Neuromorphics公司）
Mixed-precision Deep Neural Networks achieve the energy efficiency and throughput needed for hardware deployment, particularly when the resources are limited, without sacrificing accuracy. However, the optimal per-layer bit precision that preserves accuracy is not easily found, especially with the abundance of models, datasets, and quantization techniques that creates an enormous search space. In order to tackle this difficulty, a body of literature has emerged recently, and several frameworks that achieved promising accuracy results have been proposed. In this paper, we start by summarizing t…
MCU-MixQ: A HW/SW Co-optimized Mixed-precision Neural Network Design Framework for MCUs
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；North China Electric Power University（华北电力大学）
Eindhoven University of Technology（埃因霍温理工大学）；NXP Semiconductors（恩智浦半导体）
Bayesian Optimization Mixed-Precision Neural Architecture Search (BOMP-NAS) is an approach to quantization-aware neural architecture search (QA-NAS) that leverages both Bayesian optimization (BO) and mixed-precision quantization (MP) to efficiently search for compact, high performance deep neural networks. The results show that integrating quantization-aware fine-tuning (QAFT) into the NAS loop is a necessary step to find networks that perform well under low-precision quantization: integrating it allows a model size reduction of nearly 50\% on the CIFAR-10 dataset. BOMP-NAS is able to find neu…
Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the exact quantization scheme. Previous methods either examine only a small manually-designed search space or utilize a cumbersome neural architecture search to explore the vast search space. These approaches cannot lead to an optimal quantization scheme efficiently. This work proposes bit-level sparsity quantization (BSQ) to tackle the mixed-precision quantization …
Graduate Institute of Electrical Engineering, National Taiwan University（台湾大学电机工程学研究所）
Recently, deep convolutional neural networks (CNNs) have achieved many eye-catching results. However, deploying CNNs on resource-constrained edge devices is constrained by limited memory bandwidth for transmitting large intermediated data during inference, i.e., activation. Existing research utilizes mixed-precision and dimension reduction to reduce computational complexity but pays less attention to its application for activation compression. To further exploit the redundancy in activation, we propose a learnable mixed-precision and dimension reduction co-design system, which separates channe…
Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to account for the different sensitivities of different filters and is suboptimal. Mixed-precision networks address this problem, by tuning the bit-width to individual filter requirements. In this work, the problem of optimal mixed-precision network search (MPS) is considered. To circumvent its difficulties of discrete search space and combinatorial optimization, a …
Quantization is the key method for reducing inference latency, power and memory footprint of generative AI models. However, accuracy often degrades sharply when activations are quantized below eight bits. Recent work suggests that invertible linear transformations (e.g. rotations) can aid quantization, by reparameterizing feature channels and weights. In this paper, we propose \textit{Sequence Transformation and Mixed Precision} (STaMP) quantization, a novel strategy that applies linear transformations along the \textit{sequence} dimension to exploit the strong local correlation in language an…
