Related papers: MILJS : Brand New JavaScript Libraries for Matrix …

Large Neighbourhood Search (LNS) is a powerful heuristic framework for solving Mixed-Integer Programming (MIP) problems. However, designing effective variable selection strategies in LNS remains challenging, especially for diverse sets of…

Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes. Solutions based on locality-sensitive hashing (LSH) as well as…

Language models are now capable of solving tasks that require dealing with long sequences consisting of hundreds of thousands of tokens. However, they often fail on tasks that require repetitive use of simple rules, even on sequences that…

With the increasing popularity of cloud based machine learning (ML) techniques there comes a need for privacy and integrity guarantees for ML data. In addition, the significant scalability challenges faced by DRAM coupled with the high…

Mixed Integer Linear Programming (MILP) is a well-known approach for the cryptanalysis of a symmetric cipher. A number of MILP-based security analyses have been reported for non-linear (SBoxes) and linear layers. Researchers proposed word-…

Function-as-a-Service (FaaS) has raised a growing interest in how to "tame" serverless computing to enable domain-specific use cases such as data-intensive applications and machine learning (ML), to name a few. Recently, several systems…

One of the most promising applications of mathematical knowledge management is search: Even if we restrict attention to the tiny fragment of mathematics that has been formalized, the amount exceeds the comprehension of an individual human.…

General Matrix Multiplication (GEMM) is a critical kernel in high-performance computing and deep learning. While modern architectures like ARM's Scalable Matrix Extension (SME) introduce dedicated hardware for matrix operations, existing…

Visualization, querying, statistical analysis and mid-long-term scheduling are common concerns for any observatory. HILTS is a Java tool developed for the Herschel project to address all these issues in a unified way.

Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating…

Extracting actionable information rapidly from data produced by instruments such as the Linac Coherent Light Source (LCLS-II) and Advanced Photon Source Upgrade (APS-U) is becoming ever more challenging due to high (up to TB/s) data rates.…

Mixed-integer linear programming (MILP) is widely employed for modeling combinatorial optimization problems. In practice, similar MILP instances with only coefficient variations are routinely solved, and machine learning (ML) algorithms are…

Mercury is a federated metadata harvesting, search and retrieval tool based on both open source and software developed at Oak Ridge National Laboratory. It was originally developed for NASA, and the Mercury development consortium now…

Machine learning is driving development across many fields in science and engineering. A simple and efficient programming language could accelerate applications of machine learning in various fields. Currently, the programming languages…

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…

Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for…

Sequential social dilemmas pose a significant challenge in the field of multi-agent reinforcement learning (MARL), requiring environments that accurately reflect the tension between individual and collective interests. Previous benchmarks…

Open source machine learning (ML) libraries enable developers to integrate advanced ML functionality into their own applications. However, popular ML libraries, such as TensorFlow, are not available natively in all programming languages and…

Compressed bitmap indexes are used in systems such as Git or Oracle to accelerate queries. They represent sets and often support operations such as unions, intersections, differences, and symmetric differences. Several important systems…

The present state of the art in analytics requires high upfront investment of human effort and computational resources to curate datasets, even before the first query is posed. So-called pay-as-you-go data curation techniques allow these…