Results 211 to 220 of about 1,862,731 (241)

Learning hyperparameter optimization initializations

2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2015
Hyperparameter optimization is often done manually or by using a grid search. However, recent research has shown that automatic optimization techniques are able to accelerate this optimization process and find hyperparameter configurations that lead to better models.
Martin Wistuba, Nicolas Schilling, Lars Schmidt-Thieme   +2 more
openaire   +2 more sources

Hyperparameter optimization in learning systems

Journal of Membrane Computing, 2019
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +3 more sources

Results for "Optimizing hyperparameters"

2020
Output from optimizing hyperparmeters, find scripts on https://github.com/asreview/paper-optimizing ...
Gerbrich Ferdinands, Rens van de Schoot, Jonathan de Bruin   +2 more
openaire   +1 more source

LiDAR-in-the-Loop Hyperparameter Optimization

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Félix Goudreault, Dominik Scheuble, Mario Bijelic, Nicolas Robidoux, Felix Heide   +4 more
openaire   +1 more source

On Hyperparameter Optimization in Learning Systems.

2019
We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm. These procedures mirror two ways of computing gradients for recurrent neural networks and have different trade-offs in terms of running time and space requirements.
Franceschi L., Donini M., Frasconi P., Pontil M.   +3 more
openaire   +2 more sources

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

IEEE Transactions on Neural Networks and Learning Systems, 2023
Sam Kwong, Jian-Yu Li
exaly  

SLURM-Managed HyperParameter Optimization.

Hyperparameter optimization (HPO) is essential for achieving state-of-the-art performance in machine learning, yet it is computationally demanding, particularly on shared or resource-constrained clusters. We present a system that integrates the Asynchronous Successive Halving Algorithm (ASHA) with SEML, the SLURM Experiment Management Library - an ...
Chattopadhyay, Anusha, Borras, Hendrik, Klein, Bernhard, Fröning, Holger   +3 more
openaire   +2 more sources

On the use of acquisition function-based Bayesian optimization method to efficiently tune SVM hyperparameters for structural damage detection

Structural Control and Health Monitoring, 2021
Goutam Chakraborty, Anand Kumar Agrawal
exaly  

Optimization and application of the distribution of relaxation times based on characteristic frequency resolution and hyperparameters

Journal of Power Sources, 2022
Tiancai Ma, Yanbo Yang, Dong Zhu
exaly  

Scalable Meta-Bayesian Based Hyperparameters Optimization for Machine Learning

Communications in Computer and Information Science, 2023
Adeel Ahmad, Mourad Bouneffa, Moncef Garouani   +2 more
exaly