Importance sampling is widely used to improve the efficiency of deep neural network (DNN) training by reducing the variance of gradient estimators. However, efficiently assessing the variance reduction relative to uniform sampling remains challenging due to computational overhead. This paper proposes a method for estimating variance reduction during DNN training using only minibatches sampled under importance sampling. By leveraging the proposed method, the paper also proposes an effective minibatch size to enable automatic learning rate adjustment. An absolute metric to quantify the efficiency of importance sampling is also introduced as well as an algorithm for real-time estimation of importance scores based on moving gradient statistics. Theoretical analysis and experiments on benchmark datasets demonstrated that the proposed algorithm consistently reduces variance, improves training efficiency, and enhances model accuracy compared with current importance-sampling approaches while maintaining minimal computational overhead.
University of New South Wales（新南威尔士大学）；UNSW Business School（新南威尔士大学商学院）
The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is overwhelming empirical evidence in the literature showing its success, there is relatively little research exploring why the reparameterization trick is so effective. We explore this under the idealized assumptions that the variational approximation is a mean-field Gaussian density and that the log of the joint density of the model parameters and the data is a quadr…
The Chinese University of Hong Kong（香港中文大学）；Huawei Technologies Co. Ltd（华为技术有限公司）
A good parallelization strategy can significantly improve the efficiency or reduce the cost for the distributed training of deep neural networks (DNNs). Recently, several methods have been proposed to find efficient parallelization strategies but they all optimize a single objective (e.g., execution time, memory consumption) and produce only one strategy. We propose FT, an efficient algorithm that searches for an optimal set of parallelization strategies to allow the trade-off among different objectives. FT can adapt to different scenarios by minimizing the memory consumption when the number o…
Huazhong University of Science and Technology（华中科技大学）；Baidu Research（百度研究院）；Nanyang Technological University（南洋理工大学）
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a second descent. Through bias-variance decomposition, recent studies revealed that the bell-shaped variance is the major cause of model-wise double descent (when the DNN is widened gradually). This paper investigates epoch-wise double descent, i.e., the test error of a DNN also shows double descent as the number of training epoches increases. By extending the…
The Ohio State University（俄亥俄州立大学）；Dartmouth College（达特茅斯学院）
Recent work has focused on data-driven learning of the evolution of unknown systems via deep neural networks (DNNs), with the goal of conducting long time prediction of the evolution of the unknown system. Training a DNN with low generalization error is a particularly important task in this case as error is accumulated over time. Because of the inherent randomness in DNN training, chiefly in stochastic optimization, there is uncertainty in the resulting prediction, and therefore in the generalization error. Hence, the generalization error can be viewed as a random variable with some probabilit…
City University of Hong Kong（香港城市大学）；Baidu USA LLC（百度美国有限责任公司）
Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead. Traditional model pruning methods such as l-1 pruning that evaluates the channel significance for DNN pay too much attention to the local analysis of each channel and make use of the magnitude of the entire feature while ignoring its relevance to the batch normalization (BN) and ReLU layer after each convolutional operation. To overcome these problems, we propose a new model pruning method from a new perspective of gradient flow in this paper. Specifically, we first theoretically analyze the channe…
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it is hardly used in the training phase because the training phase involves dense matrix-multiplication using General-Purpose Computation on Graphics Processors (GPGPU), which endorse the regular and structural data layout. In this paper, we first propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and online gen…
This paper gives an overview of our ongoing work on the design space exploration of efficient deep neural networks (DNNs). Specifically, we cover two aspects: (1) static architecture design efficiency and (2) dynamic model execution efficiency. For static architecture design, different from existing end-to-end hardware modeling assumptions, we conduct full-stack profiling at the GPU core level to identify better accuracy-latency trade-offs for DNN designs. For dynamic model execution, different from prior work that tackles model redundancy at the DNN-channels level, we explore a new dimension …
University of Missouri（密苏里大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Systolic array-based deep neural network (DNN) accelerators have recently gained prominence for their low computational cost. However, their high energy consumption poses a bottleneck to their deployment in energy-constrained devices. To address this problem, approximate computing can be employed at the cost of some tolerable accuracy loss. However, such small accuracy variations may increase the sensitivity of DNNs towards undesired subtle disturbances, such as permanent faults. The impact of permanent faults in accurate DNNs has been thoroughly investigated in the literature. Conversely, the…
University of Technology Sydney（悉尼科技大学）；CSIRO’s Data61（澳大利亚联邦科学与工业研究组织数据61中心）；North Carolina State University（北卡罗来纳州立大学）
Deep neural networks (DNNs), are widely used in many industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, prior work has shown the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Hence, ensuring the robustness of deep learning is not an option but a priority to enhance business and consumer confidence. Previous studies mostly focus on the d…
Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
Computer Engineering Carleton University Ottawa, Canada（计算机工程 卡尔顿大学渥太华加拿大）；School of Information Technology Carleton University Ottawa, Canada（信息科技学院 卡尔顿大学渥太华加拿大）
Although federated learning (FL) has recently been proposed for efficient distributed training and data privacy protection, it still encounters many obstacles. One of these is the naturally existing statistical heterogeneity among clients, making local data distributions non independently and identically distributed (i.e., non-iid), which poses challenges for model aggregation and personalization. For FL with a deep neural network (DNN), privatizing some layers is a simple yet effective solution for non-iid problems. However, which layers should we privatize to facilitate the learning process?…
Microsoft Research Asia（微软亚洲研究院）；Communication University of China（中国传媒大学）
Time-variant factors often occur in real-world full-duplex communication applications. Some of them are caused by the complex environment such as non-stationary environmental noises and varying acoustic path while some are caused by the communication system such as the dynamic delay between the far-end and near-end signals. Current end-to-end deep neural network (DNN) based methods usually model the time-variant components implicitly and can hardly handle the unpredictable time-variance in real-time speech enhancement. To explicitly capture the time-variant components, we propose a dynamic ker…
Ytech – KWAI incorporation（Ytech – KWAI公司）；Samsung Research China – Beijing (SRC-B)（三星中国研究院 - 北京（SRC-B））
As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well. In this paper, we provide a novel perspective on these issues using the gradient signal to noise ratio (GSNR) of parameters during training process of DNNs. The GSNR of a parameter is defined as the ratio between its gradient's squared mean and variance, over the data distribution. Based on several approximations, we establish a quantitative relationship between model parameters' GSNR and the generalization gap. This relationship i…
The E-commerce platform has become the principal battleground where people search, browse and pay for whatever they want. Critical as is to improve the online shopping experience for customers and merchants, how to find a proper approach for user intent prediction are paid great attention in both industry and academia. In this paper, we propose a novel user intent prediction model, TPG-DNN, to complete the challenging task, which is based on adaptive gated recurrent unit (GRU) loss function with multi-task learning. We creatively use the GRU structure and total probability formula as the loss …
With the wide development of black-box machine learning algorithms, particularly deep neural network (DNN), the practical demand for the reliability assessment is rapidly rising. On the basis of the concept that `Bayesian deep learning knows what it does not know,' the uncertainty of DNN outputs has been investigated as a reliability measure for the classification and regression tasks. However, in the image-caption retrieval task, well-known samples are not always easy-to-retrieve samples. This study investigates two aspects of image-caption embedding-and-retrieval systems. On one hand, we qua…
With the increasing adoption of Deep Neural Network (DNN) models as integral parts of software systems, efficient operational testing of DNNs is much in demand to ensure these models' actual performance in field conditions. A challenge is that the testing often needs to produce precise results with a very limited budget for labeling data collected in field. Viewing software testing as a practice of reliability estimation through statistical sampling, we re-interpret the idea behind conventional structural coverages as conditioning for variance reduction. With this insight we propose an efficie…
Princeton University（普林斯顿大学）；University of California, Berkeley（加州大学伯克利分校）
Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we propose novel Gradient Estimation black-box attacks for adversaries with query access to the target model's class probabilities, which do not rely on transferability. We also propose strategies to decouple the number of queries required to generate each adversarial sample from the dimensionality of the input. An iterative variant of our attack achieves close…
While nowadays most gradient-based optimization methods focus on exploring the high-dimensional geometric features, the random error accumulated in a stochastic version of any algorithm implementation has not been stressed yet. In this work, we propose a universal principle which reduces the random error accumulation by exploiting statistic information hidden in mini-batch gradients. This is achieved by regularizing the learning-rate according to mini-batch variances. Due to the complementarity of our perspective, this regularization could provide a further improvement for stochastic implement…
School of Electrical and Computer Engineering University of California, San Diego（加州大学圣地亚哥分校电气与计算机工程学院）
Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad convergence. In this paper, we propose \textbf{Filter Gradient Decent}~(FGD), an efficient stochastic optimization algorithm that makes the consistent estimation of the local gradient by solving an adaptive filtering problem with different design of filters. Our method reduces variance in stochastic gradient descent by incorporating the historical states to enha…
Duke University（杜克大学）；University of California Berkeley（加州大学伯克利分校）
Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemble training method explores different training algorithms or settings on multiple sub-models with the same model architecture, which lead to significant burden on memory and computation cost of the ensemble model. Meanwhile, the heurtsically induced diversity may not lead to significant performance gain. We propose a new prespective on exploring the intrinsic diversity within a model architecture to build efficient D…
Training deep neural networks (DNNs) is a computationally expensive job, which can take weeks or months even with high performance GPUs. As a remedy for this challenge, community has started exploring the use of more efficient data representations in the training process, e.g., block floating point (BFP). However, prior work on BFP-based DNN accelerators rely on a specific BFP representation making them less versatile. This paper builds upon an algorithmic observation that we can accelerate the training by leveraging multiple BFP precisions without compromising the finally achieved accuracy. B…
DNN accelerators provide efficiency by leveraging reuse of activations/weights/outputs during the DNN computations to reduce data movement from DRAM to the chip. The reuse is captured by the accelerator's dataflow. While there has been significant prior work in exploring and comparing various dataflows, the strategy for assigning on-chip hardware resources (i.e., compute and memory) given a dataflow that can optimize for performance/energy while meeting platform constraints of area/power for DNN(s) of interest is still relatively unexplored. The design-space of choices for balancing compute an…
Politecnico di Torino（都灵理工大学）；Technische Universität Wien (TU Wien)（维也纳工业大学（维也纳技术大学））；New York University Abu Dhabi（纽约大学阿布扎比分校）
Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models but are indistinguishable for a human being. For example, an external attack can modify an image adding noises invisible for a human eye, but a DNN model misclassified the image. A key objective for developing robust DNN models is to use a learning algorithm that is fast but can also give model that is robust against different types of adversarial attacks. Especially for adversarial training, enormously long training…
Universidad de Valladolid（巴利亚多利德大学）；University of San Francisco（旧金山大学）
Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most informative image regions and rely on them to classify the complete image. The most recent work, Vision Transformer (ViT), shows its strong performance in both traditional and fine-grained classification tasks. In this work, we propose a multi-stage ViT framework for fine-grained image classification tasks, which localizes the informative image regions withou…
A traditional approach to initialization in deep neural networks (DNNs) is to sample the network weights randomly for preserving the variance of pre-activations. On the other hand, several studies show that during the training process, the distribution of stochastic gradients can be heavy-tailed especially for small batch sizes. In this case, weights and therefore pre-activations can be modeled with a heavy-tailed distribution that has an infinite variance but has a finite (non-integer) fractional moment of order $s$ with $s<2$. Motivated by this fact, we develop initialization schemes for ful…
Batch Normalization (BN) has been a standard component in designing deep neural networks (DNNs). Although the standard BN can significantly accelerate the training of DNNs and improve the generalization performance, it has several underlying limitations which may hamper the performance in both training and inference. In the training stage, BN relies on estimating the mean and variance of data using a single minibatch. Consequently, BN can be unstable when the batch size is very small or the data is poorly sampled. In the inference stage, BN often uses the so called moving mean and moving varia…
Kitami Institute of Technology（北见工业大学）；Samurai Labs（武士实验室）
In this research. we analyze the potential of Feature Density (HD) as a way to comparatively estimate machine learning (ML) classifier performance prior to training. The goal of the study is to aid in solving the problem of resource-intensive training of ML models which is becoming a serious issue due to continuously increasing dataset sizes and the ever rising popularity of Deep Neural Networks (DNN). The issue of constantly increasing demands for more powerful computational resources is also affecting the environment, as training large-scale ML models are causing alarmingly-growing amounts o…
