paper-with-me

Papers

Is One Hyperparameter Optimizer Enough?

2018-07-29 · Huy Tu, Vivek Nair

Hyperparameter tuning is the black art of automatically finding a good combination of control parameters for a data miner. While widely applied in empirical Software Engineering, there has not been much discussion on which hyperparameter tuner is best for software analytics. To address this gap in the literature, this paper applied a range of hyperparameter optimizers (grid search, random search, differential evolution, and Bayesian optimization) to defect prediction problem. Surprisingly, no hyperparameter optimizer was observed to be `best' and, for one of the two evaluation measures studied here (F-measure), hyperparameter optimization, in 50\% cases, was no better than using default configurations. We conclude that hyperparameter optimization is more nuanced than previously believed. While such optimization can certainly lead to large improvements in the performance of classifiers used in software analytics, it remains to be seen which specific optimizers should be applied to a new dataset.

📄 PDF Abstract BibTeX arXiv:1807.11112

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationHyperparameter Optimization

Similar Papers 제목 키워드 기반

Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

2019-10-25 · ICML 2020 1 · Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi 외

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparame…

Benchmarking

A Statistical Analysis for Per-Instance Evaluation of Stochastic Optimizers: How Many Repeats Are Enough?

2025-03-20 · Moslem Noori, Elisabetta Valiante, Thomas Van Vaerenbergh, Masoud Mohseni 외

A key trait of stochastic optimizers is that multiple runs of the same optimizer in attempting to solve the same problem can produce different results. As a result, their performance is evaluated over several repeats, or…

Benchmarking

On Empirical Comparisons of Optimizers for Deep Learning

2019-10-11 · Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee 외

Selecting an optimizer is a central step in the contemporary deep learning pipeline. In this paper, we demonstrate the sensitivity of optimizer comparisons to the hyperparameter tuning protocol. Our findings suggest that…

BenchmarkingDeep Learning

Should I try multiple optimizers when fine-tuning pre-trained Transformers for NLP tasks? Should I tune their hyperparameters?

2024-02-10 · Nefeli Gkouti, Prodromos Malakasiotis, Stavros Toumpis, Ion Androutsopoulos

NLP research has explored different neural model architectures and sizes, datasets, training objectives, and transfer learning techniques. However, the choice of optimizer during training has not been explored as extensi…

Transfer Learning

Fine-Tuning Adaptive Stochastic Optimizers: Determining the Optimal Hyperparameter $ε$ via Gradient Magnitude Histogram Analysis

2023-11-20 · Gustavo Silva, Paul Rodriguez

Stochastic optimizers play a crucial role in the successful training of deep neural network models. To achieve optimal model performance, designers must carefully select both model and optimizer hyperparameters. However,…

Language ModelingLanguage ModellingMachine Translation