arXiv research

The recent advances in deep neural networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-constrained computing devices. Model compression techniques can address the computation issue of deep inference on embedded devices. This technique is …

Iterative AutoML improves ASR model compression by 5x without WER degradation.

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained …

Modern deep learning models are often trained in parallel over a collection of distributed machines to reduce training time. In such settings, communication of model updates among machines becomes a significant performance bottleneck and various lossy update compression techniques have been proposed to alleviate this p…

Unified framework compresses GANs up to 47x with minimal quality loss.

Real-world data typically contain repeated and periodic patterns. This suggests that they can be effectively represented and compressed using only a few coefficients of an appropriate basis (e.g., Fourier, Wavelets, etc.). However, distance estimation when the data are represented using different sets of coefficients i…

Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested along with different inference implementation characteristics. Adopting model com…

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size.As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained e…

Proposes a new linearity-based neural network compression method.

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity explicitly in terms of its bit-size. Then, we formalize the problem of neural netwo…

New methods reduce private federated learning communication automatically.

This dissertation improves classical compression techniques using deep learning.

Data compression is a popular technique for improving the efficiency of data processing workloads such as SQL queries and more recently, machine learning (ML) with classical batch gradient methods. But the efficacy of such ideas for mini-batch stochastic gradient descent (MGD), arguably the workhorse algorithm of moder…

Compression-based similarity measures are effectively employed in applications on diverse data types with a basically parameter-free approach. Nevertheless, there are problems in applying these techniques to medium-to-large datasets which have been seldom addressed. This paper proposes a similarity measure based on com…

To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing their representations to disregard information that is not relevant to the task. However, empirical evid…

Study shows LLC correlates with neural network compressibility.

This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.

Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To alleviate this problem, several scalar quantization techniques have been developed to compress the gradients. But these techniques could perform …

Layer fusion reduces deep neural network layers with minimal loss in accuracy.

Deep Neural Networks (DNNs) are applied in a wide range of usecases. There is an increased demand for deploying DNNs on devices that do not have abundant resources such as memory and computation units. Recently, network compression through a variety of techniques such as pruning and quantization have been proposed to r…

Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we p…

Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze th…

Deep neural network pruning and quantization techniques have demonstrated it is possible to achieve high levels of compression with surprisingly little degradation to test set accuracy. However, this measure of performance conceals significant differences in how different classes and images are impacted by model compre…

Survey on pruning CNN models to reduce size for edge devices.

Proposes a method to train neural networks directly on compressed text data.

As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression metho…

Pruning is an efficient model compression technique to remove redundancy in the connectivity of deep neural networks (DNNs). Computations using sparse matrices obtained by pruning parameters, however, exhibit vastly different parallelism depending on the index representation scheme. As a result, fine-grained pruning ha…

The paper uses information geometry to analyze model compression techniques, focusing on operator factorization.

The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such as weight pruning or quantization. In this paper, we present a novel scheme for l…

DoCoFL compresses model updates for cross-device federated learning.

Compressed Monte Carlo improves efficiency in Bayesian inference.

This paper offers an overview of neural network compression techniques.

We propose and analyze a new type of stochastic first order method: gradient descent with compressed iterates (GDCI). GDCI in each iteration first compresses the current iterate using a lossy randomized compression technique, and subsequently takes a gradient step. This method is a distillation of a key ingredient in t…

New study reveals how heavy-tailed SGD dynamics lead to compressible neural networks.

Asynchronous computation and gradient compression have emerged as two key techniques for achieving scalability in distributed optimization for large-scale machine learning. This paper presents a unified analysis framework for distributed gradient methods operating with staled and compressed gradients. Non-asymptotic bo…

DP-Net uses dynamic programming for efficient deep neural network compression.

Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore specialized areas for exploration and design of large spaces in terms of size, spe…

Randomized matrix compression techniques, such as the Johnson-Lindenstrauss transform, have emerged as an effective and practical way for solving large-scale problems efficiently. With a focus on computational efficiency, however, forsaking solutions quality and accuracy becomes the trade-off. In this paper, we investi…

Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clo…

Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural networks (CNNs), however, well-known low-rank approximation methods, such as Tucker or CP decomposition, result in degraded model accuracy becau…

We show that model compression can improve the population risk of a pre-trained model, by studying the tradeoff between the decrease in the generalization error and the increase in the empirical risk with model compression. We first prove that model compression reduces an information-theoretic bound on the generalizati…

Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need for compression techniques that can achieve significant compression wit…

Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervis…

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient compression techniques are needed that are computationally friendly, applicable to …

Paper compresses ViTs models by 60% with minimal accuracy loss.

Deep neural networks (DNNs) have become the state-of-the-art technique for machine learning tasks in various applications. However, due to their size and the computational complexity, large DNNs are not readily deployable on edge devices in real-time. To manage complexity and accelerate computation, network compression…

The success of deep neural networks in many real-world applications is leading to new challenges in building more efficient architectures. One effective way of making networks more efficient is neural network compression. We provide an overview of existing neural network compression methods that can be used to make neu…

We propose a novel appearance-based gesture recognition algorithm using compressed domain signal processing techniques. Gesture features are extracted directly from the compressed measurements, which are the block averages and the coded linear combinations of the image sensor's pixel values. We also improve both the co…