Related papers: Resource-Adaptive Successive Doubling for Hyperpar…

This work proposes and studies the distributed resource allocation problem in asynchronous and stochastic settings. We consider a distributed system with multiple workers and a coordinating server with heterogeneous computation and…

Deep neural networks (DNNs) exploit many layers and a large number of parameters to achieve excellent performance. The training process of DNN models generally handles large-scale input data with many sparse features, which incurs high…

We introduce ordered transfer hyperparameter optimisation (OTHPO), a version of transfer learning for hyperparameter optimisation (HPO) where the tasks follow a sequential order. Unlike for state-of-the-art transfer HPO, the assumption is…

We present two novel hyperparameter optimization strategies for optimization of deep learning models with a modular architecture constructed of multiple subnetworks. As complex networks with multiple subnetworks become more frequently…

Heterogeneous computing is becoming mainstream in all scopes. This new era in computer architecture brings a new paradigm called Accelerator Level Parallelism (ALP). In ALP, accelerators are used concurrently to provide unprecedented levels…

In this paper, we review the key figures of merit to assess the performance of advanced random access (RA) schemes exploiting physical layer coding, repetitions and collision resolution techniques. We then investigate RA modeling aspects…

In view of the tremendous computing power jump of modern RISC processors the interest in parallel computing seems to be thinning out. Why use a complicated system of parallel processors, if the problem can be solved by a single powerful…

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple…

Hadoop MapReduce is a framework for distributed storage and processing of large datasets that is quite popular in big data analytics. It has various configuration parameters (knobs) which play an important role in deciding the performance…

Background: Embedded feature selection in high-dimensional data with very small sample sizes requires optimized hyperparameters for the model building process. For this hyperparameter optimization, nested cross-validation must be applied to…

Horizontal Pod Auto-scalers (HPAs) are crucial for managing resource allocation in microservice architectures to handle fluctuating workloads. However, traditional HPAs fail to address resource disruptions caused by faults, cyberattacks,…

In recent years, large amounts of data have been generated, and computer power has kept growing. This scenario has led to a resurgence in the interest in artificial neural networks. One of the main challenges in training effective neural…

To leverage data and computation capabilities of mobile devices, machine learning algorithms are deployed at the network edge for training artificial intelligence (AI) models, resulting in the new paradigm of edge learning. In this paper,…

Industry is rapidly moving towards fully autonomous and interconnected systems that can detect and adapt to changing conditions, including machine hardware faults. Traditional methods for adding hardware fault tolerance to machines involve…

Modern societies have developed insatiable demands for more computation capabilities. Exploiting implicit parallelism to provide automatic performance improvement remains a central goal in engineering future general-purpose computing…

Many operational systems collect high-dimensional timeseries data about users/systems on key performance metrics. For instance, ISPs, content distribution networks, and video delivery services collect quality of experience metrics for user…

Real-life parallel machine scheduling problems can be characterized by: (i) limited information about the exact task duration at scheduling time, and (ii) an opportunity to reschedule the remaining tasks each time a task processing is…

The multistage robust unit commitment (UC) is of paramount importance for achieving reliable operations considering the uncertainty of renewable realizations. The typical affine decision rule method and the robust feasible region method may…

One of the most critical issues in machine learning is the selection of appropriate hyper parameters for training models. Machine learning models may be able to reach the best training performance and may increase the ability to generalize…

In conventional federated hyperdimensional computing (HDC), training larger models usually results in higher predictive performance but also requires more computational, communication, and energy resources. If the system resources are…