Related papers: The LevelArray: A Fast, Practical Long-Lived Renam…

Faced with continuously increasing scale of data, original back-propagation neural network based machine learning algorithm presents two non-trivial challenges: huge amount of data makes it difficult to maintain both efficiency and…

Reverse time migration (RTM) is an algorithm widely used in the oil and gas industry to process seismic data. It is a computationally intensive task that suits well in parallel computers. Methods such as RTM can be parallelized in shared…

Regularization plays a vital role in the context of deep learning by preventing deep neural networks from the danger of overfitting. This paper proposes a novel deep learning regularization method named as DL-Reg, which carefully reduces…

In this era of large-scale data, distributed systems built on top of clusters of commodity hardware provide cheap and reliable storage and scalable processing of massive data. Here, we review recent work on developing and implementing…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we propose the random parallel stochastic algorithm (RAPSA). We…

Byte-addressable non-volatile memory (NVRAM) supports persistent storage with low latency and high bandwidth. Complex data structures in it ought to be updated transactionally, so that they remain recoverable at all times. Traditional…

Efficiently reranking documents retrieved from information retrieval (IR) pipelines to enhance overall quality of Retrieval-Augmented Generation (RAG) system remains an important yet challenging problem. Recent studies have highlighted the…

Developers routinely work with source files whose variable names are generic or misleading, and with teams moving quickly, many functions are left undocumented. This slows comprehension, increases the risk of subtle bugs, and makes it…

Retrieval-Augmented Generation (RAG) is a crucial method for mitigating hallucinations in Large Language Models (LLMs) and integrating external knowledge into their responses. Existing RAG methods typically employ query rewriting to clarify…

Artificial neural networks have advanced due to scaling dimensions, but conventional computing faces inefficiency due to the von Neumann bottleneck. In-memory computation architectures, like memristors, offer promise but face challenges due…

Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their…

The increasing use of cloud computing and remote execution have made program security especially important. Code obfuscation has been proposed to make the understanding of programs more complicated to attackers. In this paper, we exploit…

Recurrent Neural Networks (RNNs) have been a prominent concept within artificial intelligence. They are inspired by Biological Neural Networks (BNNs) and provide an intuitive and abstract representation of how BNNs work. Derived from the…

We describe a substring search problem that arises in group presentation simplification processes. We suggest a two-level searching model: skip and match levels. We give two timestamp algorithms which skip searching parts of the text where…

Low latency services such as credit-card fraud detection and website targeted advertisement rely on Big Data platforms (e.g., Lucene, Graphchi, Cassandra) which run on top of memory managed runtimes, such as the JVM. These platforms,…

Resampling algorithms are a useful approach to deal with imbalanced learning in multilabel scenarios. These methods have to deal with singularities in the multilabel data, such as the occurrence of frequent and infrequent labels in the same…

Deep Learning Recommendation Models (DLRMs) underpin personalized services but face a critical freshness-accuracy tradeoff due to massive parameter synchronization overheads. Production DLRMs deploy decoupled training/inference clusters,…

We present a simple, work-optimal and synchronization-free solution to the problem of stably merging in parallel two given, ordered arrays of m and n elements into an ordered array of m+n elements. The main contribution is a new, simple,…

As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…