Related papers: Data Formats in Analytical DBMSs: Performance Trad…
Modern enterprise platforms increasingly depend on distributed microservices, analytical data platforms, and external APIs to construct composite responses for applications. Orchestrating data retrieval across these heterogeneous systems is…
Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned with the target task. In practice, demonstrations are…
Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs…
Distributed systems can be very large and complex. The various considerations that influence their design can result in a substantial specification, which requires a structured framework that has to be managed successfully. The purpose of…
Optical proximity correction (OPC) is a widely-used resolution enhancement technique (RET) for printability optimization. Recently, rigorous numerical optimization and fast machine learning are the research focus of OPC in both academia and…
As data volumes grow across applications, analytics of large amounts of data is becoming increasingly important. Big data processing frameworks such as Apache Hadoop, Apache AsterixDB, and Apache Spark have been built to meet this demand. A…
The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…
We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes acquisition costs whilst still yielding accurate predictions.…
The multidimensional, heterogeneous, and temporal nature of speech databases raises interesting challenges for representation and query. Recently, annotation graphs have been proposed as a general-purpose representational framework for…
By 2025, there are zettabytes of data generated every year. The size and complexity of modern large-scale computing infrastructures like High-Performance Computing (HPC) systems continue to evolve and become complex, leaving us wondering…
This document is part of original research work by the authors in a bid to explore new fields for applying Data Mining Techniques. The sample data is part of a large data set from University of Maryland (UMD) and outlines how more…
Despite the vast body of literature on Active Learning (AL), there is no comprehensive and open benchmark allowing for efficient and simple comparison of proposed samplers. Additionally, the variability in experimental settings across the…
Tabular data represent one of the most prevalent data formats in applied machine learning, largely because they accommodate a broad spectrum of real-world problems. Existing literature has studied many of the shortcomings of neural…
The Hybrid Online Learning Problem, where features are drawn i.i.d. from an unknown distribution but labels are generated adversarially, is a well-motivated setting positioned between statistical and fully-adversarial online learning. Prior…
Tabular data remain the predominant format for real-world applications. Yet, developing effective neural models for tabular data remains challenging due to heterogeneous feature types and complex interactions occurring at multiple scales.…
This chapter provides an extended overview about Reduced Order Models (ROMs), with a focus on their features in terms of efficiency and accuracy. In particular, the aim is to browse the more common ROM frameworks, considering both intrusive…
In the current context of Big Data, a multitude of new NoSQL solutions for storing, managing, and extracting information and patterns from semi-structured data have been proposed and implemented. These solutions were developed to relieve…
The performance of worst-case optimal join algorithms depends on the order in which the join attributes are processed. Selecting good orders before query execution is hard, due to the large space of possible orders and unreliable execution…
As real-time analysis of the new data become increasingly compelling, more organizations deploy Hybrid Transactional/Analytical Processing (HTAP) systems to support real-time queries on data recently generated by online transaction…
Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…