Results 41 to 50 of about 1,872,984 (299)

Automatic Termination for Hyperparameter Optimization

, 2021
Bayesian optimization (BO) is a widely popular approach for the hyperparameter optimization (HPO) in machine learning. At its core, BO iteratively evaluates promising configurations until a user-defined budget, such as wall-clock time or number of iterations, is exhausted. While the final performance after tuning heavily depends on the provided budget,
Makarova, Anastasia, Shen, Huibin, Perrone, Valerio, Klein, Aaron, Faddoul, Jean Baptiste, Krause, Andreas, Seeger, Matthias, Archambeau, Cedric   +7 more
openaire   +4 more sources

Immunocomputing-Based Approach for Optimizing the Topologies of LSTM Networks

IEEE Access, 2021
This paper aims to automatically design optimal LSTM topologies using the clonal selection algorithm (CSA) to solve text classification tasks such as sentiment analysis and SMS spam classification.
Ali Al Bataineh, Devinder Kaur
doaj   +1 more source

Squirrel: A Switching Hyperparameter Optimizer

CoRR, 2020
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach switches between different optimizers. Since the team names on the competition's leaderboard were randomly generated "alliteration nicknames", consisting of an adjective and an ...
Noor H. Awad, Gresa Shala, Difan Deng, Neeratyoy Mallik, Matthias Feurer 0001, Katharina Eggensperger, André Biedenkapp, Diederick Vermetten, Hao Wang 0025, Carola Doerr, Marius Lindauer, Frank Hutter   +11 more
openaire   +3 more sources

Improving classification accuracy of fine-tuned CNN models: Impact of hyperparameter optimization

Heliyon
The immense popularity of convolutional neural network (CNN) models has sparked a growing interest in optimizing their hyperparameters. Discovering the ideal values for hyperparameters to achieve optimal CNN training is a complex and time-consuming task,
Mikolaj Wojciuk, Zaneta Swiderska-Chadaj, Krzysztof Siwek, Arkadiusz Gertych   +3 more
doaj   +1 more source

Metalearning for Hyperparameter Optimization [PDF]

, 2022
SummaryThis chapter describes various approaches for the hyperparameter optimization (HPO) and combined algorithm selection and hyperparameter optimization problems (CASH). It starts by presenting some basic hyperparameter optimization methods, including grid search, random search, racing strategies, successive halving and hyperband. Next, it discusses
Brazdil, Pavel, van Rijn, Jan N., Soares, Carlos, Vanschoren, Joaquin   +3 more
openaire   +2 more sources

Bayesian optimization of hyperparameters from noisy marginal likelihood estimates

, 2023
Bayesian models often involve a small set of hyperparameters determined by maximizing the marginal likelihood. Bayesian optimization is an iterative method where a Gaussian process posterior of the underlying function is sequentially updated by new ...
Mattias Villani, Stockhammar, Pär,, Gustafsson, Oskar,, Villani, Mattias,, Oskar Gustafsson, Stockhammar, Paer,, Pär Stockhammar   +6 more
core   +1 more source

Theoretical Aspects in Penalty Hyperparameters Optimization

Mediterranean Journal of Mathematics, 2023
AbstractLearning processes play an important role in enhancing understanding and analyzing real phenomena. Most of these methodologies revolve around solving penalized optimization problems. A significant challenge arises in the choice of the penalty hyperparameter, which is typically user-specified or determined through Grid search approaches.
Esposito F., Selicato L., Sportelli C.
openaire   +5 more sources

A Comparison of AutoML Hyperparameter Optimization Tools For Tabular Data

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2023
The performance of machine learning (ML) methods for classification and regression tasks applied to tabular datasets is sensitive to hyperparameters values.
Prativa Pokhrel, Alina Lazar
doaj   +1 more source

Overtuning in Hyperparameter Optimization

CoRR
Accepted at the Fourth Conference on Automated Machine Learning (Methods Track).
Lennart Schneider, Bernd Bischl, Matthias Feurer 0001   +2 more
openaire   +4 more sources

Improving Deep Learning-Based Recommendation Attack Detection Using Harris Hawks Optimization

Applied Sciences, 2022
Recommendation attack attempts to bias the recommendation results of collaborative recommender systems by injecting malicious ratings into the rating database. A lot of methods have been proposed for detecting such attacks.
Quanqiang Zhou, Cheng Huang, Liangliang Duan   +2 more
doaj   +1 more source