Multi objective hyperparameter tuning via random search on deep learning models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
This research examines the efficacy of random search (RS) in hyperparameter tuning, comparing its performance to baseline methods namely manual search and grid search. Our analysis spans various deep learning (DL) architectures-multilayer perceptron (MLP), convolutional neural network (CNN), and AlexNet implemented on prominent benchmark datasets of Modified National Institute of Standards and Technology (MNIST) and Canadian Institute for Advanced Research-10 (CIFAR-10). In the context of this study, the evaluation will be adopting a multi-objective framework, navigating the delicate trade-offs between conflicting performance metrics, including accuracy, F1-score, and model parameter size. The primary objective of employing a multi-objective evaluation framework is to enhance the understanding regarding the interactions of these performance metrics interact and influence each other. In real-world scenarios, DL models often need to strike a balance between these conflicting objectives. This research adds to the increasing wealth of knowledge in hyperparameter tuning for DL models and serves as a reference point for practitioners seeking to optimize their DL architectures. The results of our analysis are positioned to provide invaluable insights into the intricate balancing act required during the process of hyperparameter fine-tuning. These insights will contribute to the ongoing advancement of best practices in optimizing DL models and facilitating the ongoing optimization of the DL models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it