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 “"Memory Efficiency"”.

  1. Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers

    … variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a memory-efficient graph transformer for node classification, capable of handling graphs with thousands of nodes while maintaining accuracy. …

    mit Repository record for Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers (opens in a new tab)

  2. Fireworks: A Fast, Efficient and Safe Serverless Framework

    … from highly consolidated environment, and (3) memory efficiency problem from unpredictable function invocations. These problems not only degrade performance but also lowers the economic benefits of Cloud providers. In this work, we propose VM-level pre-JIT snapshot and develop Fireworks to …

    vt Repository record for Fireworks: A Fast, Efficient and Safe Serverless Framework (opens in a new tab)

  3. SlimGuard: Design and Implementation of a Memory Efficient and Secure Heap Allocator

    … severe threat. State-of-the-art secure dynamic memory allocators can offer protection, however their memory consumption is high, making them suboptimal in many situations. We introduce sys, a secure allocator whose design is driven by memory efficiency. Among other features, sys uses an …

    vt Repository record for SlimGuard: Design and Implementation of a Memory Efficient and Secure Heap Allocator (opens in a new tab)

  4. Fine-grain dataflow model and algorithms for visualization systems

    … dataflow visualization systems have serious memory efficiency problems when processing large data sets. In this thesis, we have identified a class of visualization algorithms that require sublinear memory space and are suitable for implementation in these systems. These algorithms are so …

    uiuc Repository record for Fine-grain dataflow model and algorithms for visualization systems (opens in a new tab)

  5. An end-to-end benchmarking framework for retrieval-augmented generation systems

    … regarding throughput, latency, and memory efficiency at scale—remains largely unexplored. However, current RAG benchmarking efforts are predominantly accuracy-centric, focusing on metrics like precision and recall while neglecting the implications of the underlying retrieval …

    uiuc Repository record for An end-to-end benchmarking framework for retrieval-augmented generation systems (opens in a new tab)

  6. Stochastic Sea Ice Modeling with the Dynamically Orthogonal Equations

    … we assess and show significant computational and memory efficiency compared to the direct Monte Carlo method.

    mit Repository record for Stochastic Sea Ice Modeling with the Dynamically Orthogonal Equations (opens in a new tab)

  7. Accelerating the Jacobi Iteration for Solving Linear Systems of Equations using Theory, Machine Learning, and High Performance Computing

    … of linear solver algorithms which respect the memory hierarchy of these hardware architectures to achieve the best performance. This thesis offers two key components towards the development of a memory efficient linear solver algorithm tailored towards high performance computing (HPC) systems. …

    mit Repository record for Accelerating the Jacobi Iteration for Solving Linear Systems of Equations using Theory, Machine Learning, and High Performance Computing (opens in a new tab)

  8. Sparse Kernel feature extraction

    … the learned model and increase computational and memory requirements. One approach to this problem is to extract appropriate features. General approaches such as Principal Components Analysis (PCA) are successful for a variety of applications, however they can be improved upon by targeting feature …

    soton Repository record for Sparse Kernel feature extraction (opens in a new tab)

  9. Probabilistic Programming with Low-Level, High-Performance GPU Programmable Inference

    … with fine-grained control over runtime and memory profiles. GenCUDA extends the Gen probabilistic programming architecture by providing a dynamic modeling language (DML) that allows users to write performance-critical sections of generative functions as CUDA kernels while maintaining …

    mit Repository record for Probabilistic Programming with Low-Level, High-Performance GPU Programmable Inference (opens in a new tab)

  10. Learning compact hashing codes with complex objectives from multiple sources for large scale similarity search

    … similarity search due to their computational and memory efficiency. These hashing methods design compact binary codes to represent data examples so that similar examples are mapped into similar codes. This dissertation addresses five major problems for utilizing supervised information from …

    purdue-thes Repository record for Learning compact hashing codes with complex objectives from multiple sources for large scale similarity search (opens in a new tab)

  11. Time of Day and Age Differences in the Components of Working Memory

    … the effects of time of day on short-term memory efficiency in older and younger adults. Forty-five young (18-35 years of age) and thirty-six older (over 60 years of age) adults were selected for participation. Subjects were tested individually at 0900 hrs, 1400 hrs or 2000 hrs. Two …

    nodak Repository record for Time of Day and Age Differences in the Components of Working Memory (opens in a new tab)

  12. Novel Monte Carlo Methods for Large-Scale Linear Algebra Operations

    … datasets, including fast approximated results, memory efficiency, reduced data accesses, natural parallelism, and inherent fault tolerance. In this dissertation, we present new Monte Carlo methods to accommodate a set of fundamental and ubiquitous large-scale linear algebra operations, including …

    odu Repository record for Novel Monte Carlo Methods for Large-Scale Linear Algebra Operations (opens in a new tab)

  13. Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning

    … learning new tasks, in some cases advocating a memory buffer that grows in proportion to the number of tasks. However, we offer another perspective, which is that mitigating local-task fitness during learning is as important as attempting to preserve existing knowledge. We posit the existence of …

    vt Repository record for Referencing Unlabelled World Data to Prevent Catastrophic Forgetting in Class-incremental Learning (opens in a new tab)

  14. Development of the random ray method of neutral particle transport for high-fidelity nuclear reactor simulation

    … To date, however, the time to solution and memory requirements for a general full core high fidelity 3D simulation have rendered such calculations impractical, even using leadership class supercomputers. Reactor designers have instead relied on calibrated methods that are accurate only …

    mit Repository record for Development of the random ray method of neutral particle transport for high-fidelity nuclear reactor simulation (opens in a new tab)

  15. Cyber security visualization effectiveness

    … cognitive activators and alerts, (4) working memory load, (5) threat scoring system and (6) the colour usage management. To evaluate effectiveness in our framework, we developed several use cases: (1) VisualProgger - a real-time security visualization analytic application (web and mobile …

    waikato-masters Repository record for Cyber security visualization effectiveness (opens in a new tab)

  16. Efficient Processing of Spiking Neural Networks: A Memory-Based Approach

    … systems in terms of functionality and processing efficiency. Spiking neural networks (SNNs) are widely used as the computing model for the neuromorphic system. The neurons in the SNN communicate using spikes, which allows the SNN to be efficiently implemented on hardware. In addition, the SNNs are …

    trento Repository record for Efficient Processing of Spiking Neural Networks: A Memory-Based Approach (opens in a new tab)

  17. Efficient and Composable Adaptation for Cross-Lingual Transfer

    … performance; and (iii) how to improve the efficiency of PEFT both in and beyond the context of cross-lingual transfer. The main contributions of this thesis are as follows: we first propose MAD-G, a hypernetwork method which learns to generate bottleneck adapters (a form of PEFT module) for …

    cambridge Repository record for Efficient and Composable Adaptation for Cross-Lingual Transfer (opens in a new tab)

  18. Neuromorphic Learning Systems for Supervised and Unsupervised Applications

    … for improved computation speed and energy efficiency. In this thesis, we address these two problems and apply our techniques to different cognitive applications.</p> <p>This thesis first presents the self-structured confabulation network for anomaly detection. Among the machine learning …

    syracuse-diss Repository record for Neuromorphic Learning Systems for Supervised and Unsupervised Applications (opens in a new tab)

  19. LEU+ to HALEU nuclear fuel cycle transitions and dynamic reactor models

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms

    uiuc Repository record for LEU+ to HALEU nuclear fuel cycle transitions and dynamic reactor models (opens in a new tab)