Related papers: Aggregation in the Mirror Space (AIMS): Fast, Accu…
Federated learning (FL) is a distributed Machine Learning (ML) framework that is capable of training a new global model by aggregating clients' locally trained models without sharing users' original data. Federated learning as a service…
Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing…
The mirror descent algorithm is known to be effective in situations where it is beneficial to adapt the mirror map to the underlying geometry of the optimization model. However, the effect of mirror maps on the geometry of distributed…
Machine Learning (ML) is used for developing wall functions for Improved Delayed Detached Eddy Simulations (IDDES). The ML model is based on KDtree which essentially is a fast look-up table. It searches the nearest target datapoint(s) for…
Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent…
Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT…
In-context learning (ICL) offers a promising paradigm for universal medical image analysis, enabling models to perform diverse image processing tasks without retraining. However, current ICL models for medical imaging remain limited in two…
Machine learning (ML), especially deep learning is made possible by the availability of big data, enormous compute power and, often overlooked, development tools or frameworks. As the algorithms become mature and efficient, more and more ML…
Binaural reproduction for headphone-centric listening has become a focal point in ongoing research, particularly within the realm of advancing technologies such as augmented and virtual reality (AR and VR). The demand for high-quality…
One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different from the widely-used…
The Distributed Messaging Systems (DMSs) used in IoT systems require timely and reliable data dissemination, which can be achieved through configurable parameters. However, the high-dimensional configuration space makes it difficult for…
We present DASH (Deception-Augmented Shared mental model for Human-machine teaming), a novel framework that enhances mission resilience by embedding proactive deception into Shared Mental Models (SMM). Designed for mission-critical…
It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point…
Reconfigurable distributed antenna and reflecting surface (RDARS) is a promising architecture for future sixth-generation (6G) wireless networks. In particular, the dynamic working mode configuration for the RDARS-aided system brings an…
Recently, the reconfigurable intelligent surface (RIS), benefited from the breakthrough on the fabrication of programmable meta-material, has been speculated as one of the key enabling technologies for the future six generation (6G)…
This paper addresses the problem of accurate localization for quadrupedal robots operating in narrow tunnel-like environments. Due to the long and homogeneous characteristics of such scenarios, LiDAR measurements often provide weak…
Decentralized Multi-agent Learning (DML) enables collaborative model training while preserving data privacy. However, inherent heterogeneity in agents' resources (computation, communication, and task size) may lead to substantial variations…
Recently, Multimodal Learning (MML) has gained significant interest as it compensates for single-modality limitations through comprehensive complementary information within multimodal data. However, traditional MML methods generally use the…
The data needed for machine learning (ML) model training, can reside in different separate sites often termed data silos. For data-intensive ML applications, data silos pose a major challenge: the integration and transformation of data…
5G D2D Communication promises improvements in energy and spectral efficiency, overall system capacity, and higher data rates. However, to achieve optimum results it is important to select wisely the Transmission mode of the D2D Device to…