Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strategy to alleviate resource usage, it unavoidably results in the loss of information. We introduce Lossless Compressed Memory Attention (LoMA), a novel approach that enables lossless compression of the KV cache, thereby reducing the memory and computational demands during autoregressive generation. LoMA incorporates a specialized training or fine-tuning precedure alongside an autoregressive generation algorithm optimized for the compressed context. Our method compresses the KV cache after every $tc$ generated tokens with a compression ratio of $c$ and a target compressed length $t$, and this process occurs within a single inference pass without dependency on auxiliary models. We engineered an efficient training scheme involving specific inputs, attention masks, and position identifiers to instill this compression capability. Experimental validation has demonstrated that LoMA significantly reducing computational consumption and memory usage through achieving lossless KV cache compression.
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
University of Washington（华盛顿大学）；HSE University（高等经济大学）；Yandex（扬德克斯）；Skoltech（斯科尔科沃科学技术研究院）；IST Austria（奥地利科学技术研究所）；ETH Zurich（苏黎世联邦理工学院）；NeuralMagic（神经魔法公司）
In recent years, several point cloud geometry compression methods that utilize advanced deep learning techniques have been proposed, but there are limited works on attribute compression, especially lossless compression. In this work, we build an end-to-end multiscale point cloud attribute coding method (MNeT) that progressively projects the attributes onto multiscale latent spaces. The multiscale architecture provides an accurate context for the attribute probability modeling and thus minimizes the coding bitrate with a single network prediction. Besides, our method allows scalable coding that…
JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An auto…
Yangzhou University（扬州大学）；Institut Supérieur d'Électronique de Paris（巴黎高等电子学院）；Polytechnique Montreal（蒙特利尔理工学院）；Westlake University（西湖大学）；Sorbonne University（索邦大学）
Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise the following several aspects: the research objective is not data reconstruction but feature representation; the performance evaluation of data recovery is neglected; it is hard to achieve lossless data reconstruction by pure autoencoders, even by pure deep learning. This paper aims for image reconstruction of autoencoders, employs cascade decoders-based autoencoders, perfects t…
Qualcomm AI Research（高通人工智能研究院）；Eindhoven University of Technology（埃因霍温理工大学）
Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance from a (quantized) latent representation, coupled with a prior that is used to losslessly compress these latents. Due to limitations on model capacity and imperfect optimization and generalization, such models will suboptimally compress test data in general. However, one of the great strengths of learned compression is that if the test-time data distr…
The Hebrew University of Jerusalem（耶路撒冷希伯来大学）；Tel Aviv University（特拉维夫大学）
Ensemble methods are among the state-of-the-art predictive modeling approaches. Applied to modern big data, these methods often require a large number of sub-learners, where the complexity of each learner typically grows with the size of the dataset. This phenomenon results in an increasing demand for storage space, which may be very costly. This problem mostly manifests in a subscriber based environment, where a user-specific ensemble needs to be stored on a personal device with strict storage limitations (such as a cellular device). In this work we introduce a novel method for lossless compr…
Lossless Model Compression via Joint Low-Rank Factorization Optimization
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）；Peng Cheng Laboratory（鹏城实验室）；the School of Microelectronics, South China University of Technology（华南理工大学微电子学院）
Locally Differentially Private (LDP) Reports are commonly used for collection of statistics and machine learning in the federated setting. In many cases the best known LDP algorithms require sending prohibitively large messages from the client device to the server (such as when constructing histograms over large domain or learning a high-dimensional model). This has led to significant efforts on reducing the communication cost of LDP algorithms. At the same time LDP reports are known to have relatively little information about the user's data due to randomization. Several schemes are known tha…
IBM Almaden Research Center（IBM阿尔马登研究中心）；Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Saarland University（萨尔兰大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
To handle vast amounts of data, it is natural and popular to compress vectors and matrices. When we compress a vector from size $N$ down to size $n \ll N$, it certainly makes it easier to store and transmit efficiently, but does it also make it easier to process? In this paper we consider lossless compression schemes, and ask if we can run our computations on the compressed data as efficiently as if the original data was that small. That is, if an operation has time complexity $T(\rm{inputsize})$, can we perform it on the compressed representation in time $T(n)$ rather than $T(N)$? We consider…
University of Maryland（马里兰大学）；Facebook AI（Facebook人工智能）
With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and da…
University of Applied Sciences of Western Switzerland（西瑞士应用科学大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Max-Planck Institute for Polymer Research（马克斯·普朗克聚合物研究所）；Wyss Center for Bio- and Neuroengineering（威斯生物与神经工程中心）；University of Geneva（日内瓦大学）；Dotphoton SA（多光子公司）
The impressive growth of data throughput in optical microscopy has triggered a widespread use of supervised learning (SL) models running on compressed image datasets for efficient automated analysis. However, since lossy image compression risks to produce unpredictable artifacts, quantifying the effect of data compression on SL applications is of pivotal importance to assess their reliability, especially for clinical use. We propose an experimental method to evaluate the tolerability of image compression distortions in 2D and 3D cell segmentation SL tasks: predictions on compressed data are co…
MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models
Technical University of Munich (TUM)（慕尼黑工业大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Imperial College London（帝国理工学院）；Florida State University（佛罗里达州立大学）；Institute for Advanced Study, TUM (TUM-IAS)（慕尼黑工业大学高等研究院）；TUM University Hospital（慕尼黑工业大学医院）
