paper-with-me

홈 › Papers

Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

2018-07-18 · Arber Zela, Aaron Klein, Stefan Falkner, Frank Hutter

While existing work on neural architecture search (NAS) tunes hyperparameters in a separate post-processing step, we demonstrate that architectural choices and other hyperparameter settings interact in a way that can render this separation suboptimal. Likewise, we demonstrate that the common practice of using very few epochs during the main NAS and much larger numbers of epochs during a post-processing step is inefficient due to little correlation in the relative rankings for these two training regimes. To combat both of these problems, we propose to use a recent combination of Bayesian optimization and Hyperband for efficient joint neural architecture and hyperparameter search.

📄 PDF Abstract BibTeX arXiv:1807.06906

Code (3)

Nathnos/Article-Reproduction-Deep-Learning-Efficient-Joint-Neural-Architecture-and-Hyperparameter-Search
arberzela/EfficientNAS pytorch
automl/EfficientNAS pytorch

Tasks

Bayesian OptimizationNeural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

2022-11-29 · Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo 외

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to un…

Correlated Time Series ForecastingTime SeriesTime Series AnalysisTime Series Forecasting

Efficient and Joint Hyperparameter and Architecture Search for Collaborative Filtering

2023-07-12 · Yan Wen, Chen Gao, Lingling Yi, Liwei Qiu 외

Automated Machine Learning (AutoML) techniques have recently been introduced to design Collaborative Filtering (CF) models in a data-specific manner. However, existing works either search architectures or hyperparameters…

AutoMLCollaborative Filtering

Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization

2021-05-03 · ICML Workshop AutoML 2021 7 · Julia Guerrero-Viu, Sven Hauns, Sergio Izquierdo, Guilherme Miotto 외

Neural architecture search (NAS) and hyperparameter optimization (HPO) make deep learning accessible to non-experts by automatically finding the architecture of the deep neural network to use and tuning the hyperparamete…

AutoMLHyperparameter OptimizationNeural Architecture Search

AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification

2021-10-26 · Romain Egele, Romit Maulik, Krishnan Raghavan, Bethany Lusch 외

Deep neural networks are powerful predictors for a variety of tasks. However, they do not capture uncertainty directly. Using neural network ensembles to quantify uncertainty is competitive with approaches based on Bayes…

Uncertainty Quantification

Efficient Automated Deep Learning for Time Series Forecasting

2022-05-11 · Difan Deng, Florian Karl, Frank Hutter, Bernd Bischl 외

Recent years have witnessed tremendously improved efficiency of Automated Machine Learning (AutoML), especially Automated Deep Learning (AutoDL) systems, but recent work focuses on tabular, image, or NLP tasks. So far, l…

AutoMLBayesian OptimizationDeep LearningNeural Architecture Search+3