∇-prox: Differentiable proximal algorithm modeling for large-scale optimization

Z Lai, K Wei, Y Fu, P Härtel, F Heide - ACM Transactions on Graphics …, 2023 - dl.acm.org
Tasks across diverse application domains can be posed as large-scale optimization
problems, these include graphics, vision, machine learning, imaging, health, scheduling …

IIoT data sharing based on blockchain: A multileader multifollower Stackelberg game approach

Y Jiang, Y Zhong, X Ge - IEEE Internet of Things Journal, 2021 - ieeexplore.ieee.org
The evolution of the Industrial Internet of Things (IIoTs) greatly increases the volume of data
generated by the connected IIoT devices. IIoT data are playing an increasingly important …

Distributed nonlinear model predictive control and metric learning for heterogeneous vehicle platooning with cut-in/cut-out maneuvers

MH Basiri, B Ghojogh, NL Azad… - 2020 59th IEEE …, 2020 - ieeexplore.ieee.org
Vehicle platooning has been shown to be quite fruitful in the transportation industry to
enhance fuel economy, road throughput, and driving comfort. Model Predictive Control …

Federated PCA on Grassmann Manifold for IoT Anomaly Detection

TA Nguyen, LT Le, TD Nguyen, W Bao… - IEEE/ACM …, 2024 - ieeexplore.ieee.org
With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of
devices, network security faces significant challenges, especially from anomalous activities …

Interference management in NOMA-based fog-radio access networks via scheduling and power allocation

I Randrianantenaina, M Kaneko… - IEEE Transactions …, 2020 - ieeexplore.ieee.org
This paper analyzes the integration of Non-Orthogonal Multiple Access (NOMA) in a Fog
Radio Access Network (FRAN) architecture with limited fronthaul capacity. More precisely, it …

[HTML][HTML] Decentralized intelligent multi-party competitive aggregation framework for electricity prosumers

X Cheng, R Yao, A Postnikov, Y Hu, L Varga - Applied Energy, 2024 - Elsevier
Electricity management systems are experiencing significant challenges due to the
increased penetration of distributed energy resources. Electricity flows in distribution …

Federated pca on grassmann manifold for anomaly detection in IoT networks

TA Nguyen, J He, LT Le, W Bao… - IEEE INFOCOM 2023 …, 2023 - ieeexplore.ieee.org
In the era of Internet of Things (IoT), network-wide anomaly detection is a crucial part of
monitoring IoT networks due to the inherent security vulnerabilities of most IoT devices …

[PDF][PDF] Combining ADMM and the Augmented Lagrangian Method for Efficiently Handling Many Constraints.

J Giesen, S Laue - IJCAI, 2019 - ijcai.org
Many machine learning methods entail minimizing a loss-function that is the sum of the
losses for each data point. The form of the loss function is exploited algorithmically, for …

Optimization for classical machine learning problems on the gpu

S Laue, M Blacher, J Giesen - Proceedings of the AAAI conference on …, 2022 - ojs.aaai.org
Constrained optimization problems arise frequently in classical machine learning. There
exist frameworks addressing constrained optimization, for instance, CVXPY and GENO …

Adversarial attacks on coarse-to-fine classifiers

IR Alkhouri, GK Atia - ICASSP 2021-2021 IEEE International …, 2021 - ieeexplore.ieee.org
Adversarial attacks have exposed the vulnerability of one-stage classifiers to carefully
crafted perturbations which were shown to drastically alter their predictions while remaining …