Motivated by the proliferation of mobile devices, we consider a basic form of the ubiquitous problem of time-delay estimation (TDE), but with communication constraints between two non co-located sensors. In this setting, when joint processing of the received signals is not possible, a compression technique that is tailored to TDE is desirable. For our basic TDE formulation, we develop such a joint compression-estimation strategy based on the notion of what we term "extremum encoding", whereby we send the index of the maximum of a finite-length time-series from one sensor to another. Subsequent joint processing of the encoded message with locally observed data gives rise to our proposed time-delay "maximum-index"-based estimator. We derive an exponentially tight upper bound on its error probability, establishing its consistency with respect to the number of transmitted bits. We further validate our analysis via simulations, and comment on potential extensions and generalizations of the basic methodology.
In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation. This approach hinges on decomposing any given vector, matrix, or tensor into two factors. The first factor maintains a small infinity norm, while the second exhibits a similarly constrained norm when multiplied by an orthogonal matrix. Surprisingly, the entries of factors after decomposition are well-concentrated around several peaks, which allows us to efficiently replace them with corresponding centroids for quantization purposes. We study the theoretical properties of the proposed approach and rigorously evaluate our compression algorithm in the context of next-word prediction tasks and on a set of downstream tasks for text classification. Our findings demonstrate that Kashin Quantization achieves competitive or superior quality in model performance while ensuring data compression, marking a significant advancement in the field of data quantization.
With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the large-scale scenario poses new challenges that include fault tolerance, scalability of algorithms and infrastructures, and heterogeneity in data sets, models, and resources. Due to intensive synchronization of models and sharing of data across GPUs and computing nodes during distributed training and inference processes, communication efficiency becomes the bottleneck for achieving high performance at a large scale. This article surveys the literature over the period of 2018-2023 on algorithms and technologies aimed at achieving efficient communication in large-scale distributed deep learning at various levels, including algorithms, frameworks, and infrastructures. Specifically, we first introduce efficient algorithms for model synchronization and communication data compression in the context of large-scale distributed training. Next, we introduce efficient strategies related to resource allocation and task scheduling for use in distributed training and inference. After that, we present the latest technologies pertaining to modern communication infrastructures used in distributed deep learning with a focus on examining the impact of the communication overhead in a large-scale and heterogeneous setting. Finally, we conduct a case study on the distributed training of large language models at a large scale to illustrate how to apply these technologies in real cases. This article aims to offer researchers a comprehensive understanding of the current landscape of large-scale distributed deep learning and to reveal promising future research directions toward communication-efficient solutions in this scope.
In recent years, large-scale adoption of cloud storage solutions has revolutionized the way we think about digital data storage. However, the exponential increase in data volume, especially images, has raised environmental concerns regarding power and resource consumption, as well as the rising digital carbon footprint emissions. The aim of this research is to propose a methodology for cloud-based image storage by integrating image compression technology with SuperResolution Generative Adversarial Networks (SRGAN). Rather than storing images in their original format directly on the cloud, our approach involves initially reducing the image size through compression and downsizing techniques before storage. Upon request, these compressed images will be retrieved and processed by SRGAN to generate images. The efficacy of the proposed method is evaluated in terms of PSNR and SSIM metrics. Additionally, a mathematical analysis is given to calculate power consumption and carbon footprint assesment. The proposed data compression technique provides a significant solution to achieve a reasonable trade off between environmental sustainability and industrial efficiency.
Autonomous vehicles are a promising solution to traffic congestion, air pollution, accidents, and wasted time and resources. However, remote driver intervention may be necessary for extreme situations to ensure safe roadside parking or complete remote takeover. In such cases, high-quality real-time video streaming is crucial for practical remote driving. In a preliminary study, we already presented a region of interest (ROI) HEVC data compression where the image was segmented into two categories of ROI and background, allocating more bandwidth to the ROI, yielding an improvement in the visibility of the classes that essential for driving while transmitting the background with lesser quality. However, migrating bandwidth to the large ROI portion of the image doesn't substantially improve the quality of traffic signs and lights. This work categorized the ROIs into either background, weak ROI, or strong ROI. The simulation-based approach uses a photo-realistic driving scenario database created with the Cognata self-driving car simulation platform. We use semantic segmentation to categorize the compression quality of a Coding Tree Unit (CTU) according to each pixel class. A background CTU can contain only sky, trees, vegetation, or building classes. Essentials for remote driving include significant classes such as roads, road marks, cars, and pedestrians. And most importantly, traffic signs and traffic lights. We apply thresholds to decide if the number of pixels in a CTU of a particular category is enough to declare it as belonging to the strong or weak ROI. Then, we allocate the bandwidth according to the CTU categories. Our results show that the perceptual quality of traffic signs, especially textual signs and traffic lights, improves significantly by up to 5.5 dB compared to the only background and foreground partition, while the weak ROI classes at least retain their original quality.
In the current data-intensive era, big data has become a significant asset for Artificial Intelligence (AI), serving as a foundation for developing data-driven models and providing insight into various unknown fields. This study navigates through the challenges of data uncertainties, storage limitations, and predictive data-driven modeling using big data. We utilize Robust Principal Component Analysis (RPCA) for effective noise reduction and outlier elimination, and Optimal Sensor Placement (OSP) for efficient data compression and storage. The proposed OSP technique enables data compression without substantial information loss while simultaneously reducing storage needs. While RPCA offers an enhanced alternative to traditional Principal Component Analysis (PCA) for high-dimensional data management, the scope of this work extends its utilization, focusing on robust, data-driven modeling applicable to huge data sets in real-time. For that purpose, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network, are applied to model and predict data based on a low-dimensional subset obtained from OSP, leading to a crucial acceleration of the training phase. LSTMs are feasible for capturing long-term dependencies in time series data, making them particularly suited for predicting the future states of physical systems on historical data. All the presented algorithms are not only theorized but also simulated and validated using real thermal imaging data mapping a ship's engine.
Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need methods to share the data on a wide area network (WAN) or to transfer it from edge devices to data centers. Data compression can be a solution to these problems, but an in-depth understanding of how lossy compression affects model quality is needed. Prior work largely considers a single application or compression method. We designed a systematic methodology for evaluating data reduction techniques for ML/AI, and we use it to perform a very comprehensive evaluation with 17 data reduction methods on 7 ML/AI applications to show modern lossy compression methods can achieve a 50-100x compression ratio improvement for a 1% or less loss in quality. We identify critical insights that guide the future use and design of lossy compressors for ML/AI.
We propose SketchINR, to advance the representation of vector sketches with implicit neural models. A variable length vector sketch is compressed into a latent space of fixed dimension that implicitly encodes the underlying shape as a function of time and strokes. The learned function predicts the $xy$ point coordinates in a sketch at each time and stroke. Despite its simplicity, SketchINR outperforms existing representations at multiple tasks: (i) Encoding an entire sketch dataset into a fixed size latent vector, SketchINR gives $60\times$ and $10\times$ data compression over raster and vector sketches, respectively. (ii) SketchINR's auto-decoder provides a much higher-fidelity representation than other learned vector sketch representations, and is uniquely able to scale to complex vector sketches such as FS-COCO. (iii) SketchINR supports parallelisation that can decode/render $\sim$$100\times$ faster than other learned vector representations such as SketchRNN. (iv) SketchINR, for the first time, emulates the human ability to reproduce a sketch with varying abstraction in terms of number and complexity of strokes. As a first look at implicit sketches, SketchINR's compact high-fidelity representation will support future work in modelling long and complex sketches.
In Internet of Things (IoT) networks, the amount of data sensed by user devices may be huge, resulting in the serious network congestion. To solve this problem, intelligent data compression is critical. The variational information bottleneck (VIB) approach, combined with machine learning, can be employed to train the encoder and decoder, so that the required transmission data size can be reduced significantly. However, VIB suffers from the computing burden and network insecurity. In this paper, we propose a blockchain-enabled VIB (BVIB) approach to relieve the computing burden while guaranteeing network security. Extensive simulations conducted by Python and C++ demonstrate that BVIB outperforms VIB by 36%, 22% and 57% in terms of time and CPU cycles cost, mutual information, and accuracy under attack, respectively.
Purpose:This article advocates for the development of a next-generation grid monitoring and control system designed for future grids dominated by inverter-based resources. Leveraging recent progress in generative artificial intelligence (AI), machine learning, and networking technology, we develop a physics-based AI foundation model with high-resolution synchro-waveform measurement technology to enhance grid resilience and reduce economic losses from outages. Methods and Results:The proposed framework adopts the AI Foundation Model paradigm, where a generative and pre-trained (GPT) foundation model extracts physical features from power system measurements, enabling adaptation to a wide range of grid operation tasks. Replacing the large language models used in popular AI foundation models, this approach is based on the Wiener-Kallianpur-Rosenblatt innovation model for power system time series, trained to capture the physical laws of power flows and sinusoidal characteristics of grid measurements. The pre-trained foundation model causally extracts sufficient statistics from grid measurement time series for various downstream applications, including anomaly detection, over-current protection, probabilistic forecasting, and data compression for streaming synchro-waveform data. Numerical simulations using field-collected data demonstrate significantly improved fault detection accuracy and detection speed. Conclusion:The future grid will be rich in inverter-based resources, making it highly dynamic, stochastic, and low inertia. This work underscores the limitations of existing Supervisory-Control-and-Data-Acquisition and Phasor-Measurement-Unit monitoring systems and advocates for AI-enabled monitoring and control with high-resolution synchro-waveform technology to provide accurate situational awareness, rapid response to faults, and robust network protection.
Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhanced data storage capacity but also potentially brings advantages to the development of continual machine learning (ML) systems, which learn new knowledge incrementally from sequential data. Continual ML systems often rely on storing representative samples, also known as exemplars, within a limited memory constraint to maintain the performance on previously learned data. These methods are known as memory replay-based algorithms and have proven effective at mitigating the detrimental effects of catastrophic forgetting. Nonetheless, the limited memory buffer size often falls short of adequately representing the entire data distribution. In this paper, we explore the use of image compression as a strategy to enhance the buffer's capacity, thereby increasing exemplar diversity. However, directly using compressed exemplars introduces domain shift during continual ML, marked by a discrepancy between compressed training data and uncompressed testing data. Additionally, it is essential to determine the appropriate compression algorithm and select the most effective rate for continual ML systems to balance the trade-off between exemplar quality and quantity. To this end, we introduce a new framework to incorporate image compression for continual ML including a pre-processing data compression step and an efficient compression rate/algorithm selection method. We conduct extensive experiments on CIFAR-100 and ImageNet datasets and show that our method significantly improves image classification accuracy in continual ML settings.
Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory requirement of LLMs. Quantization is an effective way of reducing the model size while maintaining good performance. However, even after quantization, LLMs may still be too big to fit entirely into the limited memory of edge or mobile devices and have to be partially loaded from the storage to complete the inference. In this case, the I/O latency of model loading becomes the bottleneck of the LLM inference latency. In this work, we take a preliminary step of studying applying data compression techniques to reduce data movement and thus speed up the inference of quantized LLM on memory-constrained devices. In particular, we discussed the compressibility of quantized LLMs, the trade-off between the compressibility and performance of quantized LLMs, and opportunities to optimize both of them jointly.
Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has been suggested that the effectiveness of BPE stems from its ability to condense text into a relatively small number of tokens. We test the hypothesis that fewer tokens lead to better downstream performance by introducing PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary. Through extensive experimentation we find this hypothesis not to be the case, casting doubt on the understanding of the reasons for effective tokenization. To examine which other factors play a role, we evaluate design decisions across all three phases of tokenization: pre-tokenization, vocabulary construction, and segmentation, offering new insights into the design of effective tokenizers. Specifically, we illustrate the importance of pre-tokenization and the benefits of using BPE to initialize vocabulary construction. We train 64 language models with varying tokenization, ranging in size from 350M to 2.4B parameters, all of which are made publicly available.
Dithering is a technique that can improve human perception of low-resolution data by reducing quantization artifacts. In this work we formalize and analytically justify two metrics for quantization artifact prominence, using them to design a novel dithering method for distortion-controlled data compression. We present theoretical entropy calculations for this dither and experimentally validate its performance on a low-rate image compression task. The result is a drastic improvement in the perceptual quality of quantized images with a lower recompression entropy than any state-of-the-art dither technique, achieving 45 points lower PIQUE at the same rate or 40% lower rate at the same PIQUE. The proposed dither is an adaptable tool applicable for use in any lossy compression system, permitting precise control of rate-distortion characteristics for both compression and recompression.
This work studies the general principles of improving the learning of language models (LMs), which aims at reducing the necessary training steps for achieving superior performance. Specifically, we present a theory for the optimal learning of LMs. We first propose an objective that optimizes LM learning by maximizing the data compression ratio in an "LM-training-as-lossless-compression" view. Then, we derive a theorem, named Learning Law, to reveal the properties of the dynamics in the optimal learning process under our objective. The theorem is then validated by experiments on a linear classification and a real-world language modeling task. Finally, we empirically verify that the optimal learning of LMs essentially stems from the improvement of the coefficients in the scaling law of LMs, indicating great promise and significance for designing practical learning acceleration methods. Our code can be found at https://aka.ms/LearningLaw.
Structural health monitoring (SHM) ensures the safety and longevity of structures like buildings and bridges. As the volume and scale of structures and the impact of their failure continue to grow, there is a dire need for SHM techniques that are scalable, inexpensive, can operate passively without human intervention, and are customized for each mechanical structure without the need for complex baseline models. We present MIDAS, a novel "deploy-and-forget" approach for automated detection and localization of damage in structures. It is a synergistic integration of entirely passive measurements from inexpensive sensors, data compression, and a mechanics-informed autoencoder. Once deployed, MIDAS continuously learns and adapts a bespoke baseline model for each structure, learning from its undamaged state's response characteristics. After learning from just 3 hours of data, it can autonomously detect and localize different types of unforeseen damage. Results from numerical simulations and experiments indicate that incorporating the mechanical characteristics into the autoencoder allows for up to a 35% improvement in the detection and localization of minor damage over a standard autoencoder. Our approach holds significant promise for reducing human intervention and inspection costs while enabling proactive and preventive maintenance strategies. This will extend the lifespan, reliability, and sustainability of civil infrastructures.
Storing and transmitting LiDAR point cloud data is essential for many AV applications, such as training data collection, remote control, cloud services or SLAM. However, due to the sparsity and unordered structure of the data, it is difficult to compress point cloud data to a low volume. Transforming the raw point cloud data into a dense 2D matrix structure is a promising way for applying compression algorithms. We propose a new lossless and calibrated 3D-to-2D transformation which allows compression algorithms to efficiently exploit spatial correlations within the 2D representation. To compress the structured representation, we use common image compression methods and also a self-supervised deep compression approach using a recurrent neural network. We also rearrange the LiDAR's intensity measurements to a dense 2D representation and propose a new metric to evaluate the compression performance of the intensity. Compared to approaches that are based on generic octree point cloud compression or based on raw point cloud data compression, our approach achieves the best quantitative and visual performance. Source code and dataset are available at https://github.com/ika-rwth-aachen/Point-Cloud-Compression.
With the exponential growth in data volume and the emergence of data-intensive applications, particularly in the field of machine learning, concerns related to resource utilization, privacy, and fairness have become paramount. This paper focuses on the textual domain of data and addresses challenges regarding encoding sentences to their optimized representations through the lens of information-theory. In particular, we use empirical estimates of mutual information, using the Donsker-Varadhan definition of Kullback-Leibler divergence. Our approach leverages this estimation to train an information-theoretic sentence embedding, called TexShape, for (task-based) data compression or for filtering out sensitive information, enhancing privacy and fairness. In this study, we employ a benchmark language model for initial text representation, complemented by neural networks for information-theoretic compression and mutual information estimations. Our experiments demonstrate significant advancements in preserving maximal targeted information and minimal sensitive information over adverse compression ratios, in terms of predictive accuracy of downstream models that are trained using the compressed data.
WiFi-enabled Internet-of-Things (IoT) devices are evolving from mere communication devices to sensing instruments, leveraging Channel State Information (CSI) extraction capabilities. Nevertheless, resource-constrained IoT devices and the intricacies of deep neural networks necessitate transmitting CSI to cloud servers for sensing. Although feasible, this leads to considerable communication overhead. In this context, this paper develops a novel Real-time Sensing and Compression Network (RSCNet) which enables sensing with compressed CSI; thereby reducing the communication overheads. RSCNet facilitates optimization across CSI windows composed of a few CSI frames. Once transmitted to cloud servers, it employs Long Short-Term Memory (LSTM) units to harness data from prior windows, thus bolstering both the sensing accuracy and CSI reconstruction. RSCNet adeptly balances the trade-off between CSI compression and sensing precision, thus streamlining real-time cloud-based WiFi sensing with reduced communication costs. Numerical findings demonstrate the gains of RSCNet over the existing benchmarks like SenseFi, showcasing a sensing accuracy of 97.4% with minimal CSI reconstruction error. Numerical results also show a computational analysis of the proposed RSCNet as a function of the number of CSI frames.
Autoencoders are a prominent model in many empirical branches of machine learning and lossy data compression. However, basic theoretical questions remain unanswered even in a shallow two-layer setting. In particular, to what degree does a shallow autoencoder capture the structure of the underlying data distribution? For the prototypical case of the 1-bit compression of sparse Gaussian data, we prove that gradient descent converges to a solution that completely disregards the sparse structure of the input. Namely, the performance of the algorithm is the same as if it was compressing a Gaussian source - with no sparsity. For general data distributions, we give evidence of a phase transition phenomenon in the shape of the gradient descent minimizer, as a function of the data sparsity: below the critical sparsity level, the minimizer is a rotation taken uniformly at random (just like in the compression of non-sparse data); above the critical sparsity, the minimizer is the identity (up to a permutation). Finally, by exploiting a connection with approximate message passing algorithms, we show how to improve upon Gaussian performance for the compression of sparse data: adding a denoising function to a shallow architecture already reduces the loss provably, and a suitable multi-layer decoder leads to a further improvement. We validate our findings on image datasets, such as CIFAR-10 and MNIST.