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 22 for “"hyperparameter optimization"”.
-
Hyperparameter Optimization of Opaque Models for Autonomous Vehicle Algorithms
Algorithms usually consist of many hyperparameters that need to be tuned to perform efficiently. It may be possible to tune a handful of parameters manually for simple algorithms however as the algorithm becomes more complex the number of hyper- parameters also increases which makes finding the …
-
Evaluating Adaptive Layer Freezing through Hyperparameter Optimization for Enhanced Fine-Tuning Performance of Language Models
Language models are initially trained on large datasets, enabling them to extract patterns and establish rich contextual connections. When dealing with data scarcity, transfer learning has become the go-to method to use these models in specialized downstream tasks via fine-tuning. However, …
-
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 …
-
Deep Mining : scaling Bayesian auto-tuning of data science pipelines
Within the automated machine learning movement, hyperparameter optimization has emerged as a particular focus. Researchers have introduced various search algorithms and open-source systems in order to automatically explore the hyperparameter space of machine learning methods. While these approaches …
-
Beyond Gradients: Using Curvature Information for Deep Learning
This thesis investigates optimization and interpretability techniques for deep learning, extending beyond gradient-based methods to incorporate curvature information. We begin by addressing the limitations of first-order optimization methods like gradient descent, which can exhibit slow convergence …
-
Data Analytics and Machine Learning Applications in Fermentation Processes and Molecular Property Prediction
… partial least square (MPLS) approaches; 2) using hyperparameter optimization methods in deep learning for the improvement of molecular property prediction, and 3) using machine learning models to predict and reduce contamination risk. For the first project, MPLS methods are used to develop …
-
MakeML : automated machine learning from data to predictions
… engineering, model selection, training, and hyperparameter optimization. After training, the user can evaluate the performance of the model and can make predictions on new data using the web interface. We show that a model generated automatically using MakeML is able to achieve accuracy …
-
Cough endpoint detection in continuous audio recordings
… spectrograms, low parameter count model design, hyperparameter optimization and finally a detailed evaluation on the achieved performance. Four main classifier architectures are considered including, logistic regression (LR), multilayer perceptron (MLP) and two convolutional neural networks (CNN) …
-
Sparse Learning of Nonlinear PDE Dynamics using Kalman Smoothing
… been incorporated into pysindy alongside hyperparameter optimization to enhance data denoising and improve differential equation discovery for several ordinary differential equation (ODE) systems. This thesis extends the use of Kalman smoothing in SINDy to partial differential equations …
-
Approximate Bayesian Modeling with Embedded Gaussian Processes
… making. Finally, we study the problem of hyperparameter optimization in probabilistic latent variable models. Although efficient algorithms are available for many classes of popular models, they cannot handle fully general models due to the appearance of intractable quantities that must be …
-
Towards searching for the best student in a Knowledge Distillation framework
… student—balancing architecture and training hyperparameters—is often hindered by the extensive and computationally intensive search required. This thesis introduces the KD-Policy-Learning (KD-PL) framework, a novel approach designed to mitigate this challenge. KD-PL integrates an explicit …
-
TOWARDS EFFICIENT LARGE-SCALE BI-LEVEL OPTIMIZATION, ALGORITHMS AND APPLICATIONS
Bi-level optimization is a mathematical framework with a long history of research, dealing with hierarchical optimization problems where one problem is nested within the other. Recently, with the rise of machine learning, bi-level optimization has regained attention as a theoretical framework …
-
Evaluating the Effects of Financial Deregulation on Bank Risk using Double Machine Learning
… techniques, cross-fitting pro- cedures, and hyperparameter optimization on the performance and interpretability of DML in applied policy settings. Our work underscores the value of integrating modern computa- tional tools into empirical regulatory analysis, offering insights for policymakers …
-
Optimizing Machine Learning Performance on Tabular Clinical Data: A Pipeline Approach
… and XGBoost), and sophisticated Bayesian hyperparameter optimization. The pipeline's dual effectiveness, both in achieving high predictive accuracy and exposing fundamental challenges, is rigorously demonstrated across two distinct clinical tabular datasets. While proving highly successful …
-
Planning under uncertainty with Bayesian nonparametric models
… pipeline, from initial prototyping through hyperparameter optimization, parallelization of large-scale experiments, and final publication-ready plotting.
-
Advanced Techniques For Prediction of Forest Above Ground Biomass Using Satellite Remote Sensing Data
… a framework developed from the combination of a hyperparameter optimization procedure and a meta-learning algorithm to set up an end-to-end automated pipeline for modelling AGB. The contribution focuses on automatic development and extraction of features from MS data as well as automatic stacking …
-
Intrusion detection by machine learning = Behatolás detektálás gépi tanulás által
… identified were synthetic sampling, advanced hyperparameter optimization, model ensembles and autoencoder networks. In addition, the dissertation set up a soft hierarchy among the different detection techniques in terms of performance and provides a brief outlook on potential future practical …
-
Investigation of Multi-Z Impurity Transport in Tokamaks using Neural Networks
… addressing areas of highest network uncertainty. Hyperparameter optimization and testing resulted in highly accurate networks. Testing set relative errors averaged over ρ = 0.4–0.7 and 0.9 show approximate deviations of 0.12 ± 0.029 for heat flux and 0.42 ± 0.095 for particle flux channels. …
-
Bilevel Optimization in the Deep Learning Era: Methods and Applications
Neural networks, coupled with their associated optimization algorithms, have demonstrated remarkable efficacy and versatility across an extensive array of tasks, encompassing image recognition, speech recognition, object detection, sentiment analysis, and more. The inherent strength of neural …
-
On Bilevel Optimization without Full Unrolls: Methods and Applications
Bilevel optimization (BLO) problems are nested optimization problems where an outer objective must be minimized subject to the optimality of an inner objective. This nested structure poses several challenges, including the cost of running full unrolls of the inner problem for each outer parameter …
Page 1 of 2