Related papers: AVATAR -- Machine Learning Pipeline Evaluation Usi…

As decarbonization agendas mature, macro-energy systems modelling studies have increasingly focused on enhanced decision support methods that move beyond least-cost modelling to improve consideration of additional objectives and tradeoffs.…

Data science relies on pipelines that are organized in the form of interdependent computational steps. Each step consists of various candidate algorithms that maybe used for performing a particular function. Each algorithm consists of…

Automated Machine Learning (AutoML) is used more than ever before to support users in determining efficient hyperparameters, neural architectures, or even full machine learning pipelines. However, users tend to mistrust the optimization…

Structured data-quality issues, such as missing values correlated with demographics, culturally biased labels, or systemic selection biases, routinely degrade the reliability of machine-learning pipelines. Regulators now increasingly demand…

Integrated circuit verification has gathered considerable interest in recent times. Since these circuits keep growing in complexity year by year, pre-Silicon (pre-SI) verification becomes ever more important, in order to ensure proper…

Missing value imputation is a crucial preprocessing step for many machine learning problems. However, it is often considered as a separate subtask from downstream applications such as classification, regression, or clustering, and thus is…

Systematic exploration of Agent-Based Models (ABMs) is challenged by the curse of dimensionality and their inherent stochasticity. We present a multi-stage pipeline integrating the systematic design of experiments with machine learning…

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment,…

Pipeline Parallelism (PP) enables large neural network training on small, interconnected devices by splitting the model into multiple stages. To maximize pipeline utilization, asynchronous optimization is appealing as it offers 100%…

Simulation testing is a fundamental approach for evaluating automated vehicles (AVs). To ensure its reliability, it is crucial to accurately replicate interactions between AVs and background traffic, which necessitates effective…

Machine learning pipelines that include a combinatorial optimization layer can give surprisingly efficient heuristics for difficult combinatorial optimization problems. Three questions remain open: which architecture should be used, how…

The Numerical Association Rule Mining paradigm that includes concurrent dealing with numerical and categorical attributes is beneficial for discovering associations from datasets consisting of both features. The process is not considered as…

With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more…

The coexistence of multiple defect categories as well as the substantial class imbalance problem significantly impair the detection of sewer pipeline defects. To solve this problem, a multi-label pipe defect recognition method is proposed…

Compiler optimization relies on sequences of passes to improve program performance. Selecting and ordering these passes automatically, known as compiler auto-tuning, is challenging due to the large and complex search space. Existing…

Representation engineering methods have recently shown promise for enabling efficient steering of model behavior. However, evaluation pipelines for these methods have primarily relied on subjective demonstrations, instead of quantitative,…

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability…

Algorithm-selection (AS) methods are essential in order to obtain the best performance from a portfolio of solvers over large sets of instances. However, many AS methods rely on an analysis phase, e.g. where features are computed by…

Machine learning (ML) models in production pipelines are frequently retrained on the latest partitions of large, continually-growing datasets. Due to engineering bugs, partitions in such datasets almost always have some corrupted features;…

Understanding performance and prioritizing resources for the maintenance of the drinking-water pipe network throughout its life-cycle is a key part of water asset management. Renovation of this vital network is generally hindered by the…