arXiv research

Method learns software resource usage from snapshots.

ATA optimizes task allocation in distributed machine learning.

PePR scores assess DL model performance per resource unit, promoting smaller, more efficient models.

PASHA optimizes model tuning for large datasets with limited resources.

FAVANO improves federated learning for resource-constrained environments.

Efficient neural networks for resource-constrained systems.

With the rapid growth of the data volume and the fast increasing of the computational model complexity in the scenario of cloud computing, it becomes an important topic that how to handle users' requests by scheduling computational jobs and assigning the resources in data center. In order to have a better perception of…

By leveraging the concept of mobile edge computing (MEC), massive amount of data generated by a large number of Internet of Things (IoT) devices could be offloaded to MEC server at the edge of wireless network for further computational intensive processing. However, due to the resource constraint of IoT devices and wir…

We study classification problems where features are corrupted by noise and where the magnitude of the noise in each feature is influenced by the resources allocated to its acquisition. This is the case, for example, when multiple sensors share a common resource (power, bandwidth, attention, etc.). We develop a method f…

Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume exces…

This work tackles resource allocation in asynchronous and stochastic systems.

There is an increasing interest in a fast-growing machine learning technique called Federated Learning, in which the model training is distributed over mobile user equipments (UEs), exploiting UEs' local computation and training data. Despite its advantages in data privacy-preserving, Federated Learning (FL) still has …

OpTorch optimizes deep learning for resource-limited environments.

Study resource allocation strategies in sequential decisions with unknown rewards.

This paper presents an assessment of global economic energy potentials for all major natural energy resources. This work is based on both an extensive literature review and calculations using natural resource assessment data. Economic potentials are presented in the form of cost-supply curves, in terms of energy flows …

Simple policy outperforms complex ones in cloud auto-scaling.

Resource-efficient oblique trees reduce neural signal classification costs.

As deep neural network (NN) methods have matured, there has been increasing interest in deploying NN solutions to "edge computing" platforms such as mobile phones or embedded controllers. These platforms are often resource-constrained, especially in energy storage and power, but state-of-the-art NN architectures are de…

This study uses LSTM and SARIMA models to forecast CPU usage in cloud computing.

This paper optimizes AI inference on edge devices with reduced communication and computation costs.

Developing active inference agents for edge devices with limited resources.

Deep learning enhances water resources management through data analysis.

Sequence-to-sequence models predict resource usage for co-scheduled jobs in data centers.

The study examines how quantum resources enhance the complexity of quantum circuits.

For massive and heterogeneous modern datasets, it is of fundamental interest to provide guarantees on the accuracy of estimation when computational resources are limited. In the application of learning to rank, we provide a hierarchy of rank-breaking mechanisms ordered by the complexity in thus generated sketch of the …

A scalable parallel BO method for asynchronous settings.

The virtualization of compute and network resources enables an unseen flexibility for deploying network services. A wide spectrum of emerging technologies allows an ever-growing range of orchestration possibilities in cloud-based environments. But in this context it remains challenging to rhyme dynamic cloud configurat…

This paper optimizes revenue and resource balance in network revenue management.

GP-TS optimizes TLM pre-training hyperparameters efficiently.

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but introduces a privacy risk since the operator of the cloud is not necessarily trustworthy.…

The study examines how alternative resource adequacy contract designs affect market participants' risk profiles and resource mix.

Survey on using large models to train smaller datasets in NLP.

Subjective expected utility theory assumes that decision-makers possess unlimited computational resources to reason about their choices; however, virtually all decisions in everyday life are made under resource constraints - i.e. decision-makers are bounded in their rationality. Here we experimentally tested the predic…

Three hard diagrams of the unknot require extra crossings to simplify.

Review of efficient neural networks for TinyML on resource-constrained devices.

Deep learning approach for efficient IoT task scheduling in MEC networks.

Transformers use ReLUs to approximate softmax efficiently.

Local SGD outperforms conventional methods in LLM training.

Study compares LSTM and ANN architectures for forex prediction, finding ANN more efficient.

Federated Learning helps IoT devices learn without central servers.

Research in automatic affect recognition has seldom addressed the issue of computational resource utilization. With the advent of ambient intelligence technology which employs a variety of low-power, resource-constrained devices, this issue is increasingly gaining interest. This is especially the case in the context of…

RL enhances cloud autoscaling by learning optimal resource allocation.

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a train…

We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has…

Quantum advantage in derivative pricing requires 8k qubits and 54M T-depth.

This paper proposes a new D2D data sharing approach to improve distributed machine learning training speed.

Paper presents a new VMBQC model with fewer parameters for better generative modeling.

New algorithm reduces online decision-making regret with efficient LP re-solving and parallel first-order method.