Related papers: The Problem with XSD Binary Floating Point Datatyp…
Conventional dataset distillation requires significant computational resources and assumes access to the entire dataset, an assumption impractical as it presumes all data resides on a central server. In this paper, we focus on dataset…
This preliminary white paper proposes a novel 8-bit floating-point data format HiFloat8 (abbreviated as HiF8) for deep learning. HiF8 features tapered precision. For normal value encoding, it provides 7 exponent values with 3-bit mantissa,…
Powder X-ray Diffraction (PXRD) and Pair Distribution Function (PDF) analysis are well-established techniques for investigation of atomic configurations in crystalline materials, and the two are related by a Fourier transformation. In PXRD…
Reversible data hiding continues to attract significant attention in recent years. In particular, an increasing number of authors focus on the higher significant bit (HSB) plane of an image which can yield more redundant space. On the other…
This article shows that any type of binary data can be defined as a collection from codewords of variable length. This feature helps us to define an Injective and surjective function from the suggested codewords to the required codewords.…
User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we…
Current critical systems commonly use a lot of floating-point computations, and thus the testing or static analysis of programs containing floating-point operators has become a priority. However, correctly defining the semantics of common…
A subspace-based approach for rate-adaptive distributed source coding (DSC) based on discrete Fourier transform (DFT) codes is developed. Punctured DFT codes can be used to implement rate-adaptive source coding, however they perform poorly…
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning.…
Machine learning models usually assume that a set of feature values used to obtain an output is fixed in advance. However, in many real-world problems, a cost is associated with measuring these features. To address the issue of reducing…
The quality of datasets is a critical issue in big data mining. More interesting things could be mined from datasets with higher quality. The existence of missing values in geographical data would worsen the quality of big datasets. To…
Large-scale numerical computations make increasing use of low-precision (LP) floating point formats and mixed precision arithmetic, which can be enhanced by the technique of stochastic rounding (SR), that is, rounding an intermediate…
Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit…
Informative data selection is a key requirement for large language models (LLMs) to minimize the amount of data required for fine-tuning, network distillation, and token pruning, enabling fast and efficient deployment, especially under…
Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…
The XMM identification (XID) programme is accumulating Optical/IR data to identify thousands of XMM sources at both high ($bII > 20^{\circ}$) and low galactic latitude. X-ray sources are divided into samples on the basis of their X-ray flux…
Raw data sizes are growing and proliferating in scientific research, driven by the success of data-hungry computational methods, such as machine learning. The preponderance of proprietary and shoehorned data formats make computations slower…
Statistical analysis of functional data is challenging due to their complex patterns, for which functional depth provides an effective means of reflecting their ordering structure. In this work, we investigate practical aspects of the…
The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time,…
Procedures based on current methods to detect sources in X-ray images are applied to simulated XMM images. All significant instrumental effects are taken into account, and two kinds of sources are considered -- unresolved sources…