Related papers: HDTCat: let's make HDT scale
Dataset condensation can be used to reduce the computational cost of training multiple models on a large dataset by condensing the training dataset into a small synthetic set. State-of-the-art approaches rely on matching the model gradients…
Several distributed system paradigms utilize Distributed Hash Tables (DHTs) to realize structured peer-to-peer (P2P) overlays. DHT structures arise as the most commonly used organizations for peers that can efficiently perform crucial…
Three-dimensional magnetic recording (3DMR) is a highly promising approach to achieving ultra-large data storage capacity in hard disk drives. One of the greatest challenges for 3DMR lies in performing sequential and correct writing of bits…
In this report we show how to manage a distributed hierarchical structure representing a file system. This structure is optimistically replicated, each user work on his local replica, and updates are sent to other replica. The different…
There has been considerable research into improving Fast Fourier Transform (FFT) performance through parallelization and optimization for specialized hardware. However, even with those advancements, processing of very large files, over 1TB…
Hyperdimensional (HD) computing is built upon its unique data type referred to as hypervectors. The dimension of these hypervectors is typically in the range of tens of thousands. Proposed to solve cognitive tasks, HD computing aims at…
The fast Fourier transform (FFT) is undoubtedly an essential primitive that has been applied in various fields of science and engineering. In this paper, we present a decomposition method for parallelization of multi-dimensional FFTs with…
Given a real-world dataset, data condensation (DC) aims to synthesize a small synthetic dataset that captures the knowledge of a natural dataset while being usable for training models with comparable accuracy. Recent works propose to…
Driven by the tremendous effort in researching novel deep learning (DL) algorithms, the training cost of developing new models increases staggeringly in recent years. We analyze GPU cluster usage statistics from a top research institute for…
In the field of database deduplication, the goal is to find approximately matching records within a database. Blocking is a typical stage in this process that involves cheaply finding candidate pairs of records that are potential matches…
Many organizations rely on data from government and third-party sources, and those sources rarely follow the same data formatting. This introduces challenges in integrating data from multiple sources or aligning external sources with…
Many research questions can be answered quickly and efficiently using data already collected for previous research. This practice is called secondary data analysis (SDA), and has gained popularity due to lower costs and improved research…
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping…
Partitioning graphs into blocks of roughly equal size such that few edges run between blocks is a frequently needed operation when processing graphs on a parallel computer. When a topology of a distributed system is known an important task…
We present ATC, a C++ library for advanced Tucker-based lossy compression of dense multidimensional numerical data in a shared-memory parallel setting, based on the sequentially truncated higher-order singular value decomposition (ST-HOSVD)…
Code retrieval, which retrieves code snippets based on users' natural language descriptions, is widely used by developers and plays a pivotal role in real-world software development. The advent of deep learning has shifted the retrieval…
Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…
Minimizing failing test cases is an important pre-processing step on the path of debugging. If much of a test case that triggered a bug does not contribute to the actual failure, then the time required to fix the bug can increase…
Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the…
Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…