Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 19 of 19 for “"communication efficient"”.
-
Toward communication-efficient and secure distributed machine learning
… machine learning requires collaboration and communication among the devices, which incur the new challenges: 1) the heavy communication overhead can be the bottleneck that slows down the training; 2) the unreliable communication and weaker control over the remote entities makes the …
-
Communication-efficient personalization in federated learning for edge devices
… algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb overfitting on heterogeneous clients, stabilize convergence, and lower both computation …
-
Communication efficient large scale distributed optimization with curvature acceleration
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01
-
Communication-efficient and privacy-preserving statistical learning with applications in high dimensional data
… deterministic, frequentist approaches for efficient model training. This work seeks to extend those frameworks by explicitly addressing the inherent heterogeneity across data sites and integrating robust mechanisms for quantifying uncertainty. To address this gap, this dissertation argues …
-
Implementation of a Multi-Agent System in Java Agent Development Framework for a large-scale fossil-fuel electrical power unit control.
… of the power in the United States and must do efficiently with more added regulation and more in the short term future. The control for these large-scale power plants can be complex but must still address several different operating objectives. Implementing advanced control for a large-scale …
-
An Identity and Certificate Manager
… ICM can be used in a variety of personal communication applications, such as chat, email, VoIP telephony, and web browsing. As part of ICM, we designed and implemented a communication-efficient protocol, called Identity and Certificate Exchange (ICE), for exchanging certificates, …
-
Investigating team collaboration in the fire department of New York using transcripts from September 11, 2001
… standard operating procedure as an indicator of efficient radio communication. Efficient radio communication expedites the process of moving the team towards their ultimate goal; on September 11, 2001, that goal was to rescue the thousands of civilians trapped in the Twin Towers. This thesis uses …
-
AI-infused security: Robust defense by bridging theory and practice
… detectors. For defenses, we develop SHIELD, an efficient defense leveraging stochastic image compression, and UnMask, a knowledge-based adversarial detection and defense framework. (2) Theoretically Principled Defense via Game Theory and ML: We develop new theories that guide defense resources …
-
The design and fabrication of an inp-based transistor-injected quantum cascade laser
… fields including chemical sensing and free-space communication. Efficient and compact coherent sources in these wavelength ranges are important for enabling practical solutions to these problems. While quantum cascade lasers (QCLs) present one appealing solution for these infrared sources, …
-
Value of information based distributed inference and planning
… valuable information. This thesis presents efficient distributed sensing and planning algorithms that improve resource planning efficiently by taking into account the obtainable Value of Information (VoI) and improve distributed sensing efficiency by ensuring agents only broadcast high value …
-
Algorithms and Systems for Scalable Multi-Agent Geometric Estimation
… conditioning. On the other hand, realworld communication networks impose operational constraints (e.g., in the form of available bandwidth) that need to be accounted for during deployment. This thesis develops algorithms and systems toward enabling scalable collaborative geometric …
-
How to keep a secret and share a public key (using polynomial commitments)
… two fundamental problems. First, we introduce communication-efficient, fully-untrusted append-only logs, which can be used to correctly distribute public keys. Our constructions have logarithmic-sized proofs for the two key operations in append-only logs: looking up public keys and verifying …
-
Online Learning for Resource Allocation in Wireless Networks: Fairness, Communication Efficiency, and Data Privacy
… allocation plays a crucial role in ensuring efficient use of the (limited) available network resources. Note that resource allocation may require knowledge of network parameters (e.g., channel state information and available power level) for package schedule. However, wireless networks …
-
Enable Intelligence on Billion Devices with Deep Learning
… hinder its deployments to edge devices, such as communication cost and data heterogeneity. </p><p>Once we obtain a learned machine learning model, the next step is to deploy the model for serving applications and services. One straightforward approach is to deploy the model on device to perform …
-
Heterogeneous Sensor Signal Processing for Inference with Nonlinear Dependence
… in Wireless Sensor Networks (WSNs), where, for communication efficiency, only local decisions are transmitted. We derive the necessary conditions for the optimal decision rules at the sensors and the FC by introducing a "hidden" random variable. An iterative algorithm is designed to search for …
-
Distributed Machine Learning in Heterogeneous Edge Networks
… where slow devices hinder training progress), communication overhead (i.e., the high cost of transferring data between devices), and device heterogeneity (i.e., variability in device capabilities). This dissertation explores the challenges of distributed machine learning in heterogeneous edge …
-
Improving federated learning performance with similarity guided feature extraction and pruning.
… on model performance with aggregation methods, communication overhead and security threats. Existing aggregation methodologies often lack generalisability across different datasets and applications. Moreover, communication efficiency remains a significant bottleneck. The frequent exchange of …
-
Some New Results in Distributed Tracking and Optimization
… on the foundation of distributed systems, and efficient distributed algorithms to run on these systems.With the rapid increase in the volume of the data being fed into these systems, storing and processing all this data at a central location becomes infeasible. Such a central \textit{server} …
-
Efficient Distributed and Multi-Modal Machine Learning in Wireless Networks
… without sharing raw data. However, devices and communication networks have limited resources, in terms of computing, energy, bandwidth, and memory to support complex distributed ML algorithms. Second, next-generation wireless networks can potentially leverage a broad range of sensing modalities, …