Related papers: CM-CASL: Comparison-based Performance Modeling of …

Machine learning and deep learning classification models are data-driven, and the model and the data jointly determine their classification performance. It is biased to evaluate the model's performance only based on the classifier accuracy…

Configuration space complexity makes the big-data software systems hard to configure well. Consider Hadoop, with over nine hundred parameters, developers often just use the default configurations provided with Hadoop distributions. The…

Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance. In pool-based active learning, accessible unlabeled data…

Large Language Models (LLMs) have demonstrated great potential in Conversational Recommender Systems (CRS). However, the application of LLMs to CRS has exposed a notable discrepancy in behavior between LLM-based CRS and human recommenders:…

In-Context Learning (ICL) is suffering from unsatisfactory performance and under-calibration due to high prior bias and unfaithful confidence. Some previous works fine-tuned language models for better ICL performance with enormous datasets…

Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardware accelerators, interconnect bandwidth, software frameworks, parallelism plans,…

This paper introduces the MCML approach for empirically studying the learnability of relational properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of…

In healthcare and biomedical applications, extreme computational requirements pose a significant barrier to adopting representation learning. Representation learning can enhance the performance of deep learning architectures by learning…

Increasingly more research areas rely on machine learning methods to accelerate discovery while saving resources. Machine learning models, however, usually require large datasets of experimental or computational results, which in certain…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Combining multiple machine learning models into an ensemble is known to provide superior performance levels compared to the individual components forming the ensemble. This is because models can complement each other in taking better…

As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform complex tasks. The task of orchestrating these models is increasingly performed by Large Language…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

Controller design faces a trade-off between robustness and performance, and the reliability of linear controllers has caused many practitioners to focus on the former. However, there is renewed interest in improving system performance to…

In the software development process, model transformation is increasingly assimilated. However, systems being developed with model transformation sometimes grow in size and become complex. Meanwhile, the performance of model transformation…

Existing self-supervised techniques have extreme computational requirements and suffer a substantial drop in performance with a reduction in batch size or pretraining epochs. This paper presents Cross Architectural - Self Supervision…

In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts…

In recent years, HPC systems and CPU architectures as their central components, have become increasingly complex, making application development and optimization quite challenging. In this respect, intuitive performance models like the…

In the era of big data, a large amount of noisy and incomplete data can be collected from multiple sources for prediction tasks. Combining multiple models or data sources helps to counteract the effects of low data quality and the bias of…

While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.…