Related papers: On the Model Update Strategies for Supervised Lear…
The Age-of-Information is an important metric for investigating the timeliness performance in information-update systems. In this paper, we study the AoI minimization problem under a new Pull model with replication schemes, where a user…
We formulate the predicted-updates dynamic model, one of the first beyond-worst-case models for dynamic algorithms, which generalizes a large set of well-studied dynamic models including the offline dynamic, incremental, and decremental…
Large scale projects increasingly operate in complicated settings whilst drawing on an array of complex data-points, which require precise analysis for accurate control and interventions to mitigate possible project failure. Coupled with a…
Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an…
Given the ever-increasing complexity of adaptable software systems and their commonly hidden internal information (e.g., software runs in the public cloud), machine learning based performance modeling has gained momentum for evaluating,…
In recent years, Data Science has become increasingly relevant as a support tool for industry, significantly enhancing decision-making in a way never seen before. In this context, the MLOps discipline emerges as a solution to automate the…
Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…
Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs.…
Large Artificial Intelligence (AI) training workloads spanning several tens of thousands of GPUs present unique power management challenges. These arise due to the high variability in power consumption during the training. Given the…
The rapid development of machine learning (ML) and artificial intelligence (AI) applications requires the training of large numbers of models. This growing demand highlights the importance of training models without human supervision, while…
Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include…
Machine learning-based performance models are increasingly being used to build critical job scheduling and application optimization decisions. Traditionally, these models assume that data distribution does not change as more samples are…
Industrial AI is transitioning from traditional deep learning models to large-scale transformer-based architectures, with the Industrial Internet of Things (IIoT) playing a pivotal role. IIoT evolves from a simple data pipeline to an…
Many key problems in machine learning and data science are routinely modeled as optimization problems and solved via optimization algorithms. With the increase of the volume of data and the size and complexity of the statistical models used…
DevOps and Artificial Intelligence (AI) are interconnected with each other. DevOps is a business-driven approach to providing quickly delivered quality software, and AI is the technology that can be used in the system to enhance its…
Artificial intelligence (AI), and especially its sub-field of Machine Learning (ML), are impacting the daily lives of everyone with their ubiquitous applications. In recent years, AI researchers and practitioners have introduced principles…
As Artificial Intelligent (AI) technology advances and increasingly large amounts of data become readily available via various Industrial Internet of Things (IIoT) projects, we evaluate the state of the art of predictive maintenance…
Model update lies at the heart of object tracking. Generally, model update is formulated as an online learning problem where a target model is learned over the online training set. Our key innovation is to \emph{formulate the model update…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…