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 244 for “"Distributed learning"”.
-
Distributed learning under resource constraints
… in control, signal processing, and machine learning applications presents numerous computational challenges. In many settings, data is distributed across numerous devices and needs to be processed, stored and communicated, naturally leading to distributed optimization problems. It is often …
-
On structured and distributed learning
… exploiting low-dimensional structure, as well as distributed methods, have been playing an ever important role in machine learning. These approaches offer a natural choice to alleviate the computational burden, albeit typically at a statistical trade-off. In this thesis, we show that a careful …
-
Probabilistic Methods for Distributed Learning
… has proliferated recently. A significant machine learning challenge concerns development of methods that efficiently model and learn from data at this scale, while retaining analysis flexibility and sophistication.</p><p>Many statistical learning problems are formulated in terms of regularized …
-
Distributed Learning with Automated Stepsizes
… We present experiments on standard machine learning problems like logistic regression, matrix factorization (gradients are not globally Lipschitz), and CIFAR-10 image classification.
-
Distributed learning in large populations
Distributed learning is the iterative process of decision-making in the presence of other decision-makers. In recent years, researchers across fields as disparate as engineering, biology, and economics have identified mathematically congruous problem formulations at the intersection of their …
-
Bidirectional TopK Sparsification for Distributed Learning
… a large amount of time. To speed up the process, distributed training is often used. One of the largest bottlenecks in distributed training is communicating gradients across different nodes. Different gradient compression techniques have been proposed to alleviate the communication bottleneck, …
-
Communication Design for Dynamic Distributed Learning Systems
Distributed learning leverages distributed data across multiple entities to collaboratively train a shared model on their collective data, without requiring local data to leave its respective entity. It has gained attention compared to non-distributed traditional learning frameworks, as it enhances …
-
Distributed learning and inference in deep models
In recent years, the size of deep learning problems has been increased significantly, both in terms of the number of available training samples as well as the number of parameters and complexity of the model. In this thesis, we considered the challenges encountered in training and inference of …
-
Distributed learning in games under bounded rationality
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-12-01
-
Breaking the dimension dependence in distributed learning
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01
-
Towards More Efficient Communication for Distributed Learning Systems
… accelerators shift the bottleneckof large-scale distributed training tasks from computation to communication. We observesignificant pressure on the communication backends of various mainstream learning systemsin multiple environments when running such tasks. Achieving efficient large scale …
-
Supporting Collective Inquiry: A Technology Framework for Distributed Learning
… framework to support smart classrooms and Distributed Technology Enhanced Learning (DTEL) called SAIL Smart Space (S3). S3 is an open-source technology framework designed to support students engaged in inquiry investigations as a knowledge community. To evaluate the effectiveness of S3 as a …
-
Fast and private distributed learning for low rank models
This dissertation focuses on fast and private distributed learning for low rank models. For this problem, we have proposed fast algorithms and, using techniques from non-convex analysis, linear algebra, and high-dimensional probability, analyzed their convergence. The results of this research have …
-
Enhancing ICT supported distributed learning through action design research
… boundaries of time and place in teaching and learning. In a distributed learning approach online technologies are blended with campus-based in person activities. In higher education, keeping up with the change creates interests and concerns, which the organization has to attend to in order to …
-
Architecture design and simulation for distributed learning classifier systems
In this thesis, we introduce the Distributed Learning Classifier System (DLCS) as a novel extension of J. H. Holland's standard learning classifier system. While the standard LCS offers effective real-time control and learning, one of its limitations is that it does not provide a mechanism for …
-
Centralized and distributed learning methods for predictive health analytics
… our work focuses on developing centralized and distributed learning methods to predict future heart- or diabetes- related hospitalizations based on patient Electronic Health Records (EHRs). We explore a variety of supervised classification methods and we present a novel likelihood ratio based …
-
Supporting orchestration of blended CSCL scenarios in distributed learning environments
El diseño y gestión en tiempo real de escenarios de aprendizaje colaborativo soportado por ordenador (en inglés, CSCL) es una tarea compleja y difícilmente realizable por profesores no expertos, que en los últimos años ha dado en denominarse "orquestación". La presente tesis doctoral profundiza en …
-
Inference under finite mixture models : distributed learning and approximate inference
… data that exhibit heterogeneity. In machine learning, they are often used as probabilistic models for clustering analysis. In the application of finite mixtures to real datasets, the most fundamental task is to learn model parameters. In modern applications, datasets are often too large to be …
Page 1 of 13