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 14 of 14 for “"Federated optimization"”.

  1. Differentially private online learning algorithms for federated optimization

    … of trade secrets. This has led to the concept of federated learning, where a federation of clients can collaborate among themselves while preserving their data. There are still some challenges faced with federated learning. Some of these challenges are addressed in this dissertation. This …

    wichita-thes Repository record for Differentially private online learning algorithms for federated optimization (opens in a new tab)

  2. Duality in structured and federated optimization : theory and applications

    The dual approach in mathematical optimization refers to a class of techniques for tackling a dual problem that arises from the original problem. Numerous notable improvements in strengthening the dual approach have been promoted in the last two decades because of its superior performance for many …

    ubc Repository record for Duality in structured and federated optimization : theory and applications (opens in a new tab) Download PDF for Duality in structured and federated optimization : theory and applications (opens in a new tab)

  3. Efficient Transmission in the Presence and Absence of Data Privacy Using Digital Twins and Federated Optimization

    … a fixed time horizon. We propose a real-time federated optimization framework in which the scheduler iteratively exchanges only aggregate signals with DTs to compute global fractional solutions without revealing private information; dependent rounding then yields implementable channel …

    mcmaster Repository record for Efficient Transmission in the Presence and Absence of Data Privacy Using Digital Twins and Federated Optimization (opens in a new tab)

  4. Advanced Quantization Techniques for Communication Efficiency and Privacy in Federated Learning, and Memory-efficient Fine-tuning of LLMs

    … role in developing communication-efficient Federated Learning (FL) algorithms, as well as in optimizing training for Large Language Models (LLMs). While it is evident that quantization can significantly enhance the efficiency of modern machine learning systems with thoughtful and …

    gatech Repository record for Advanced Quantization Techniques for Communication Efficiency and Privacy in Federated Learning, and Memory-efficient Fine-tuning of LLMs (opens in a new tab)

  5. Trajectory Prediction for Automotive Applications using Federated Learning

    … and must follow safety and privacy regulations. Federated learning (FL) enables the training of DL models to be done locally at each client (vehicle), sharing and aggregating the trained models while keeping the data local. This allows previously unreachable data to be harnessed for improved …

    chalmers Repository record for Trajectory Prediction for Automotive Applications using Federated Learning (opens in a new tab)

  6. Toward communication-efficient and secure distributed machine learning

    … SGD, to reduce the communication overhead; 2) federated optimization in asynchronous mode; 3) a framework of score-based approaches for Byzantine tolerance in distributed SGD; 4) a distributed learning system integrating all these three techniques. The proposed system provides communication …

    uiuc Repository record for Toward communication-efficient and secure distributed machine learning (opens in a new tab)

  7. From Enormous Structured Models to On-device Federated Learning: Robustness, Heterogeneity and Optimization

    … size consistently improves performance, and (3) federated learning, where model training moves to mobile devices, where the data is generated and resides. This dissertation presents diagnostic methods and new algorithms to measure and improve the robustness of machine learning models to …

    washington Repository record for From Enormous Structured Models to On-device Federated Learning: Robustness, Heterogeneity and Optimization (opens in a new tab)

  8. Federated Learning for Heterogeneous Networks: Algorithmic and System Design

    … data sources without violating user privacy. Federated Learning (FL) can facilitate collaborative machine learning without accessing user-sensitive data and has emerged as an attractive paradigm for mobile edge networks. However, federated optimization builds on a heterogeneous environment, …

    york Repository record for Federated Learning for Heterogeneous Networks: Algorithmic and System Design (opens in a new tab)

  9. Toward Federated and Multi-Modal Learning: From Optimized Edge Intelligence to Bias-Aware Foundation Models

    … learning paradigms has naturally arisen. Federated Learning (gls{fl}) index{Federated Learning} is a distributed ML framework that enables collaborative model training without sharing raw data. Each client trains a local model using its own data, and only model updates are shared with a …

    queens Repository record for Toward Federated and Multi-Modal Learning: From Optimized Edge Intelligence to Bias-Aware Foundation Models (opens in a new tab)

  10. Communication And Computation Efficient Deep Learning

    … out by a single machine. Hence, distributed optimization and inference have been widely adopted to tackle large-scale machine learning problems. Meanwhile, quantum computers that process computational tasks exponentially faster than classical machines offer an alternative solution for …

    wm-mary Repository record for Communication And Computation Efficient Deep Learning (opens in a new tab)

  11. Explainable AI and Advanced Mathematical Modeling for Radiotherapy Outcome Assessment

    … limit centralized model training. Two federated learning (FL) frameworks were developed to improve robustness and generalizability without direct data sharing. The first framework combined federated learning with a fisheye-inspired spherical image transformation and ensemble inference …

    duke Repository record for Explainable AI and Advanced Mathematical Modeling for Radiotherapy Outcome Assessment (opens in a new tab)

  12. Privacy-aware distributed machine learning

    … client capabilities, and integrating with federated strategies. This thesis addresses these challenges through four primary contributions. First, we address communication efficiency by proposing a Vector Quantized Variational Autoencoder (VQ-VAE) framework using Lookup-Free Quantization …

    manitoba Repository record for Privacy-aware distributed machine learning (opens in a new tab)

  13. Foundations of Multiple-Time-Scale Stochastic Approximation for Fast and Resilient Distributed Optimization Algorithms

    … and designing fast and resilient distributed optimization algorithms for large-scale networks. The central focus is on understanding and leveraging two-time-scale dynamics, which may arise naturally from the underlying network structure or be introduced through algorithmic design. Motivated by …

    vt Repository record for Foundations of Multiple-Time-Scale Stochastic Approximation for Fast and Resilient Distributed Optimization Algorithms (opens in a new tab)

  14. Communication-efficient Distributed Multi-resource Allocation

    … AIMD algorithm to solve a class of distributed optimization problems for multiple divisible shared resources. The algorithm is a derandomized version of the stochastic additive-increase and multiplicative-decrease (AIMD) algorithm. The developed solution uses a one-bit feedback signal for each …

    concordia Download PDF for Communication-efficient Distributed Multi-resource Allocation (opens in a new tab)