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 20 of 47 for “"Decentralized learning"”.

  1. Decentralized Learning in Stochastic and Mean-Field Games

    Multi-agent reinforcement learning (MARL) is the study of strategic interaction between multiple learning agents that coexist in a shared environment. Compared to single-agent theory, MARL theory is plagued by several inherent challenges, including decentralized information and non-stationary …

    queens Repository record for Decentralized Learning in Stochastic and Mean-Field Games (opens in a new tab)

  2. Decentralized Learning for Wireless Video Streaming with Delayed Feedback

    We study the optimal control of multiple video streams over a wireless downlink from a base-station (BS)/access point to N end-devices. The BS sends video packets to each end-device under a joint transmission power constraint, the end-devices choose how to play out the received packets, and the …

    tamu Repository record for Decentralized Learning for Wireless Video Streaming with Delayed Feedback (opens in a new tab)

  3. Enhancing optimization algorithms for non-convex settings : federated and decentralized learning

    … drawn significant attention from the machine learning community to non-convex optimization. This thesis focuses on federated and decentralized learning within the framework of non-convex optimization, aiming to deepen the understanding of the field and derive novel results. Specifically, the …

    texas Repository record for Enhancing optimization algorithms for non-convex settings : federated and decentralized learning (opens in a new tab)

  4. Seeing without revealing: Privacy-Aware Computational Cameras and Decentralized Learning Frameworks

    … whose parameters are optimized in an end-to-end learning pipeline using adversarial optimization. The results are computational cameras that achieve optimal privacy-utility trade-offs and are validated using proof-of-concept hardware. The subsequent part of the thesis examines the application of …

    rice Repository record for Seeing without revealing: Privacy-Aware Computational Cameras and Decentralized Learning Frameworks (opens in a new tab)

  5. Enhanced collaboration in between the machine learning models : bringing decentralized learning to reality

    … life, present unique opportunities for machine learning applications. Historically, due to computational limitations, machine learning tasks have been conducted on powerful centralized computers rather than on edge devices. Nowadays, as computational resources on mobile devices continue to …

    texas Repository record for Enhanced collaboration in between the machine learning models : bringing decentralized learning to reality (opens in a new tab)

  6. Mitigating effects of data heterogeneity in decentralized learning and addressing challenges of adapting foundation models

    … Chapters 2 and 3 address data heterogeneity in decentralized and federated learning, while Chapters 4 and 5 focus on the adaptation and optimization of the Segment Anything Model (SAM), a foundation model for image segmentation. We begin by tackling the challenges associated with data …

    iastate Repository record for Mitigating effects of data heterogeneity in decentralized learning and addressing challenges of adapting foundation models (opens in a new tab)

  7. Decentralized Deep Learning under Distributed Concept Drift: A Novel Approach to Dealing with Changes in Data Distributions Over Clients and Over Time

    In decentralized deep learning, clients train local models in a peer-to-peer fashion by sharing model parameters, rather than data. This allows collective model training in cases where data may be sensitive or for other reasons unable to be transferred. In this setting, variations in data …

    chalmers Repository record for Decentralized Deep Learning under Distributed Concept Drift: A Novel Approach to Dealing with Changes in Data Distributions Over Clients and Over Time (opens in a new tab)

  8. Machine learning model selection with multi-objective Bayesian optimization and reinforcement learning

    A machine learning system, including when used in reinforcement learning, is usually fed with only limited data, while aimed at training a model with good predictive performance that can generalize to an underlying data distribution. Within certain hypothesis classes, model selection chooses a …

    lmu-germany Repository record for Machine learning model selection with multi-objective Bayesian optimization and reinforcement learning (opens in a new tab)

  9. Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset

    … that the dataset is not learnable by machine learning/deep learning methods. That is, the NTGA-generated dataset is protected against unauthorized use. In this thesis, we explore the vulnerability of an NTGA-generated unlearnable CIFAR-10 dataset. Specifically, we show that by employing data …

    usf Repository record for Exploring the Vulnerability of A Neural Tangent Generalization Attack (NTGA) - Generated Unlearnable CIFAR-10 Dataset (opens in a new tab)

  10. Decentralized and Partially Decentralized Multi-Agent Reinforcement Learning

    … a pre-programmed strategy. Reinforcement learning provides a framework in which agents learn optimal behavior based on the response obtained from the environment. In this thesis, we propose various novel de- centralized, learning automaton based algorithms which can be employed by a group …

    iupui Repository record for Decentralized and Partially Decentralized Multi-Agent Reinforcement Learning (opens in a new tab)

  11. An Introduction to Federated Learning and Its Analysis

    … privacy is one of the most predominant issues. Decentralized learning is becoming popular as the data can remain within local entities by maintaining privacy. Federated Learning is a decentralized machine learning approach, where multiple clients collaboratively learn a model, without sharing …

    unlv Repository record for An Introduction to Federated Learning and Its Analysis (opens in a new tab) Download PDF for An Introduction to Federated Learning and Its Analysis (opens in a new tab)

  12. Learning in the Multi-Robot Pursuit Evasion Game

    This thesis investigates the learning issue for mobile robots playing the differential forms of the pursuit-evasion (PE) game by proposing different learning algorithms. The intended learning algorithms are used to reduce (1) the computational requirements as much as possible, without affecting the …

    carleton Repository record for Learning in the Multi-Robot Pursuit Evasion Game (opens in a new tab)

  13. Privacy-preserving continual federated learning via GANs and elastic weight consolidation

    Federated learning has already become a revolutionary technique of training machine learning models. It guarantees privacy of data since clients’ training happens in a decentralized way. When data distribution changes across time, federated learning is highly prone to nonstationary settings. Among …

    regina Repository record for Privacy-preserving continual federated learning via GANs and elastic weight consolidation (opens in a new tab)

  14. Breaking the silence : empowering adolescent girls through art

    … girls’ psychology, the power of art-making, decentralized structure, and feminist pedagogy. Grounded in this literature the author creates a 12-week art club for 7th and 8th grade girls. This club was designed to promote assertiveness and self-confidence by letting the girls lead in a …

    texas Repository record for Breaking the silence : empowering adolescent girls through art (opens in a new tab)

  15. Secure Computation and Proportionally Fair Collaboration in Federated Learning of Histopathology Images

    The prediction power of deep learning models depends on the size and quality of the training data. Having access to large-scale datasets enables the model to more precisely estimate the underlying distribution of the data. Deep models rely on training datasets that are ideally aggregated from …

    waterloo Repository record for Secure Computation and Proportionally Fair Collaboration in Federated Learning of Histopathology Images (opens in a new tab)

  16. Mutual empowerment of distributed AI and blockchain

    Due to their security, transparency, and decentralized trust model, blockchains have been integrated into a wide range of applications. Distributed and collaborative deep learning approaches, such as Federated Learning and Split Learning, are among the most prominent areas jointly explored with …

    manitoba Repository record for Mutual empowerment of distributed AI and blockchain (opens in a new tab)

  17. Power evaluation and performance enhancement of CSMA/CA based WLANs.

    … Protection (ICNIRP) limit; (2) We propose two decentralized Multiple Access Control (MAC) schemes that converge to collision-free schedules almost surely and therefore improve throughput performance. In adopting decentralized learning techniques, the convergence times of both schemes are brief. …

    maynooth Download PDF for Power evaluation and performance enhancement of CSMA/CA based WLANs. (opens in a new tab)

  18. Towards opportunistic collaborative learning in mobile environments

    … gather data to support the training of deep learning models, enabling applications on these devices to perform tasks such as image processing, next-word prediction, and content recommendation. Model training typically requires a large set of data, ideally one that exhibits a representation of …

    texas Repository record for Towards opportunistic collaborative learning in mobile environments (opens in a new tab)

  19. Diagnostics, Cooperation, and Model Selection for Modern Machine Learning

    … bring many difficulties to modeling in machine learning. To address this issue, we develop tools to handle the challenges in three fundamental and interconnected aspects of machine learning: diagnostics, improvement, and model selection.For “diagnostics,” we focus on classification problems. To …

    umn Repository record for Diagnostics, Cooperation, and Model Selection for Modern Machine Learning (opens in a new tab)

Page 1 of 3