Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTowards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization
55
0
0.0
(
0
)
Added by
Yukuan Yang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
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. Existing works only focus on the convolution or BN acceleration and no solution can alleviate both problems with satisfactory performance. Online training has gradually become a trend in resource-limited devices like mobile phones while there is still no complete technical scheme with acceptable model performance, processing speed, and computational cost. In this research, an efficient online-training quantization framework termed EOQ is proposed by combining Fixup initialization and a novel quantization scheme for DNN model compression and acceleration. Based on the proposed framework, we have successfully realized full 8-bit integer network training and removed BN in large-scale DNNs. Especially, weight updates are quantized to 8-bit integers for the first time. Theoretical analyses of EOQ utilizing Fixup initialization for removing BN have been further given using a novel Block Dynamical Isometry theory with weaker assumptions. Benefiting from rational quantization strategies and the absence of BN, the full 8-bit networks based on EOQ can achieve state-of-the-art accuracy and immense advantages in computational cost and processing speed. What is more, the design of deep learning chips can be profoundly simplified for the absence of unfriendly square root operations in BN. Beyond this, EOQ has been evidenced to be more advantageous in small-batch online training with fewer batch samples. In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.
rate research
Read More
Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle for the efficient implementation of BNN training. It also introduces undesirable dependence between samples within each batch. Inspired by the latest advance on Batch Normalization Free (BN-Free) training, we extend their framework to training BNNs, and for the first time demonstrate that BNs can be completed removed from BNN training and inference regimes. By plugging in and customizing techniques including adaptive gradient clipping, scale weight standardization, and specialized bottleneck block, a BN-free BNN is capable of maintaining competitive accuracy compared to its BN-based counterpart. Extensive experiments validate the effectiveness of our proposal across diverse BNN backbones and datasets. For example, after removing BNs from the state-of-the-art ReActNets, it can still be trained with our proposed methodology to achieve 92.08%, 68.34%, and 68.0% accuracy on CIFAR-10, CIFAR-100, and ImageNet respectively, with marginal performance drop (0.23%~0.44% on CIFAR and 1.40% on ImageNet). Codes and pre-trained models are available at: https://github.com/VITA-Group/BNN_NoBN.
Batch normalization (BN) has become a crucial component across diverse deep neural networks. The network with BN is invariant to positively linear re-scaling of weights, which makes there exist infinite functionally equivalent networks with various scales of weights. However, optimizing these equivalent networks with the first-order method such as stochastic gradient descent will converge to different local optima owing to different gradients across training. To alleviate this, we propose a quotient manifold emph{PSI manifold}, in which all the equivalent weights of the network with BN are regarded as the same one element. Then, gradient descent and stochastic gradient descent on the PSI manifold are also constructed. The two algorithms guarantee that every group of equivalent weights (caused by positively re-scaling) converge to the equivalent optima. Besides that, we give the convergence rate of the proposed algorithms on PSI manifold and justify that they accelerate training compared with the algorithms on the Euclidean weight space. Empirical studies show that our algorithms can consistently achieve better performances over various experimental settings.
Batch normalization (BN) is a popular and ubiquitous method in deep learning that has been shown to decrease training time and improve generalization performance of neural networks. Despite its success, BN is not theoretically well understood. It is not suitable for use with very small mini-batch sizes or online learning. In this paper, we propose a new method called Batch Normalization Preconditioning (BNP). Instead of applying normalization explicitly through a batch normalization layer as is done in BN, BNP applies normalization by conditioning the parameter gradients directly during training. This is designed to improve the Hessian matrix of the loss function and hence convergence during training. One benefit is that BNP is not constrained on the mini-batch size and works in the online learning setting. Furthermore, its connection to BN provides theoretical insights on how BN improves training and how BN is applied to special architectures such as convolutional neural networks.
To train large models (like BERT and GPT-3) with hundreds or even thousands of GPUs, the communication has become a major bottleneck, especially on commodity systems with limited-bandwidth TCP interconnects network. On one side large-batch optimization such as LAMB algorithm was proposed to reduce the number of communications. On the other side, communication compression algorithms such as 1-bit SGD and 1-bit Adam help to reduce the volume of each communication. However, we find that simply using one of the techniques is not sufficient to solve the communication challenge, especially on low-bandwidth Ethernet networks. Motivated by this we aim to combine the power of large-batch optimization and communication compression, but we find that existing compression strategies cannot be directly applied to LAMB due to its unique adaptive layerwise learning rates. To this end, we design a new communication-efficient algorithm, 1-bit LAMB, which introduces a novel way to support adaptive layerwise learning rates even when communication is compressed. In addition, we introduce a new system implementation for compressed communication using the NCCL backend of PyTorch distributed, which improves both usability and performance compared to existing MPI-based implementation. For BERT-Large pre-training task with batch sizes from 8K to 64K, our evaluations on up to 256 GPUs demonstrate that 1-bit LAMB with NCCL-based backend is able to achieve up to 4.6x communication volume reduction, up to 2.8x end-to-end speedup (in terms of number of training samples per second), and the same convergence speed (in terms of number of pre-training samples to reach the same accuracy on fine-tuning tasks) compared to uncompressed LAMB.
Deep neural network (DNN) accelerators received considerable attention in past years due to saved energy compared to mainstream hardware. Low-voltage operation of DNN accelerators allows to further reduce energy consumption significantly, however, causes bit-level failures in the memory storing the quantized DNN weights. In this paper, we show that a combination of robust fixed-point quantization, weight clipping, and random bit error training (RandBET) improves robustness against random bit errors in (quantized) DNN weights significantly. This leads to high energy savings from both low-voltage operation as well as low-precision quantization. Our approach generalizes across operating voltages and accelerators, as demonstrated on bit errors from profiled SRAM arrays. We also discuss why weight clipping alone is already a quite effective way to achieve robustness against bit errors. Moreover, we specifically discuss the involved trade-offs regarding accuracy, robustness and precision: Without losing more than 1% in accuracy compared to a normally trained 8-bit DNN, we can reduce energy consumption on CIFAR-10 by 20%. Higher energy savings of, e.g., 30%, are possible at the cost of 2.5% accuracy, even for 4-bit DNNs.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
