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 150 for “"Hyperparameter Optimization"”.

  1. Advancing hyperparameter optimization

    Hyperparameter optimization (HPO) is a fundamental aspect of machine learning (ML), directly influencing model performance and adaptability. As a computationally expensive black-box optimization problem, HPO requires efficient algorithms to identify optimal hyperparameter configurations. This …

    lmu-germany Repository record for Advancing hyperparameter optimization (opens in a new tab)

  2. Efficient bayesian hyperparameter optimization

    … core tasks is the automated search for the right hyperparameters of a given machine learning algorithm which in practice is often essential to achieve good performance. Compare to other optimization problems, hyperparameter optimization is usually particularly expensive, since in each iteration, …

    freiburg-diss Repository record for Efficient bayesian hyperparameter optimization (opens in a new tab)

  3. Hyperparameter Optimization for Neural Machine Translation Systems

    … processes must be made—these decisions are the hyperparameters of the system. Typically, these hyperparameters are set before training begins and remain unchanged until convergence. Traditionally, they are tuned manually based on intuition, heuristics, previous studies, or default settings …

    jhu Repository record for Hyperparameter Optimization for Neural Machine Translation Systems (opens in a new tab)

  4. Advanced hyperparameter optimization: performance modelling and efficient benchmarking

    … However, often not the method but rather its hyperparameter setting is vital for its success. Manually tuning these hyperparameters is tedious and often impossible, and, thus, there is a critical demand for efficient hyperparameter optimization (HPO) methods opening up unique opportunities and …

    freiburg-diss Repository record for Advanced hyperparameter optimization: performance modelling and efficient benchmarking (opens in a new tab)

  5. Locating Diversity in Reservoir Computing Using Bayesian Hyperparameter Optimization

    … up reservoir's internal network. We use Bayesian hyperparameter optimization to find optimal hyperparameters and explore the relationships between diversity, accuracy of model predictions, and model hyperparameters. The content regarding the VPT metric, the effects of network thinning on reservoir …

    byu Repository record for Locating Diversity in Reservoir Computing Using Bayesian Hyperparameter Optimization (opens in a new tab) Download PDF for Locating Diversity in Reservoir Computing Using Bayesian Hyperparameter Optimization (opens in a new tab)

  6. TOWARDS SCALABLE GRADIENT-BASED HYPERPARAMETER OPTIMIZATION IN DEEP NEURAL NETWORKS

    … (DNNs) is sensitive to the setting of their hyperparameters. Hyperparameter optimization is thus recognized as a crucial step in the process of applying DNNs to achieve best performance and drive industrial applications. The works described in this thesis represent the first forays into the …

    nus Repository record for TOWARDS SCALABLE GRADIENT-BASED HYPERPARAMETER OPTIMIZATION IN DEEP NEURAL NETWORKS (opens in a new tab) Download file for TOWARDS SCALABLE GRADIENT-BASED HYPERPARAMETER OPTIMIZATION IN DEEP NEURAL NETWORKS (opens in a new tab)

  7. Gradient boosting in automatic machine learning: feature selection and hyperparameter optimization

    … ebenfalls untersucht. Die Herausforderung der Hyperparameteroptimierung wird mit Fokus auf Bayesianische Optimierung und effiziente Stopping-Strategien diskutiert. Ein groß angelegter Benchmark über Hyperparameter verschiedener Lernalgorithmen, zeigt den kritischen Einfluss von Hyperparameter …

    lmu-germany Repository record for Gradient boosting in automatic machine learning: feature selection and hyperparameter optimization (opens in a new tab)

  8. Auto-WEKA : combined selection and hyperparameter optimization of supervised machine learning algorithms

    … taking into account each algorithm's set of hyperparameters, there is a staggeringly large number of possible choices. This project considers the problem of simultaneously selecting a learning algorithm and setting its hyperparameters. Previous works attack these issues separately, but this …

    ubc Repository record for Auto-WEKA : combined selection and hyperparameter optimization of supervised machine learning algorithms (opens in a new tab) Download PDF for Auto-WEKA : combined selection and hyperparameter optimization of supervised machine learning algorithms (opens in a new tab)

  9. Efficient automated deep learning via task-conditioned meta-learning and hyperparameter optimization

    … depends critically on design choices, from hyperparameters and optimization strategies to the neural network architecture itself, each of which can substantially affect performance. When a new task is encountered, these choices are typically made through expensive trial-and-error, with no …

    freiburg-diss Repository record for Efficient automated deep learning via task-conditioned meta-learning and hyperparameter optimization (opens in a new tab)

  10. Duality, Derivative-Based Training Methods and Hyperparameter Optimization for Support Vector Machines

    … and gradient-based methods for the training and hyperparameter optimization of Support Vector Machines. We show that the dualization of convex training problems is possible theoretically in a rather general formulation. For training problems following a special structure (for instance, standard …

    qucosa-diss

  11. Robust and efficient automated machine learning: systems, infrastructure and advances in hyperparameter optimization

    … search for the best models, tune their hyperparameters, and ensemble them. Hyperparameter optimization (HPO) is a core part of AutoML research and also a research field on its own as models and datasets increase in size and complexity. However, current AutoML systems and HPO methods are …

    freiburg-diss Repository record for Robust and efficient automated machine learning: systems, infrastructure and advances in hyperparameter optimization (opens in a new tab)

  12. Case study of Hyperparameter Optimization framework Optuna on a Multi-column Convolutional Neural Network

    … is essential involving appropriate values of hyperparameters. Among numerous possible values of these hyperparameters, selecting the suitable ones is certainly a time-consuming and tedious task for humans. Ongoing research for developing Automated Hyperparameter Optimization (HPO) frameworks …

    sask Repository record for Case study of Hyperparameter Optimization framework Optuna on a Multi-column Convolutional Neural Network (opens in a new tab)

  13. A Control Theoretic Approach to the Stochastic Multi-armed Bandit Problem With Applications in Hyperparameter Optimization

    … for the two problems, we propose an online hyperparameter optimizer called Hyperparameter Controller (HyperController) in Reinforcement Learning (RL) to improve the efficiency and performance of training RL neural networks. Our theoretical results demonstrate that HyperController accelerates …

    wustl Repository record for A Control Theoretic Approach to the Stochastic Multi-armed Bandit Problem With Applications in Hyperparameter Optimization (opens in a new tab)

  14. Correcting Biases in Multi-Module Neural Networks, Through Efficient Hyperparameter Optimization and Statistically Meaningful Uncertainty Quantification, with Applications to Neurological Disorders

    … neurological problems. It develops novel hyperparameter search strategies with significantly improved performance of multi-module networks for diagnoses and prognoses, and adds uncertainty quantification to empower multi-module mixed effects deep learning models with the ability to produce …

    utswmed Repository record for Correcting Biases in Multi-Module Neural Networks, Through Efficient Hyperparameter Optimization and Statistically Meaningful Uncertainty Quantification, with Applications to Neurological Disorders (opens in a new tab)

  15. Scalable Nested Optimization For Deep Learning

    Gradient-based optimization has been critical to the success of machine learning, updating a single set of parameters to minimize a single loss. A growing number of applications rely on a generalization of this, where we have a bilevel or nested optimization of which subsets of parameters update on …

    toronto-retro Repository record for Scalable Nested Optimization For Deep Learning (opens in a new tab)

  16. Healthcare innovations empowered by discriminative and generative artificial intelligence

    … (Nested and Automated Cross-validation with Hyperparameter Optimization on Supercomputers), an algorithm that integrates nested cross-validation, automated hyperparameter optimization, and high-performance computing (HPC) to more reliably estimate test performance and quantify uncertainty at …

    oklahoma-thes Repository record for Healthcare innovations empowered by discriminative and generative artificial intelligence (opens in a new tab)

Page 1 of 8