paper-with-me

Papers

Model-based Asynchronous Hyperparameter and Neural Architecture Search

2020-03-24 · Aaron Klein, Louis C. Tiao, Thibaut Lienart, Cedric Archambeau, Matthias Seeger

We introduce a model-based asynchronous multi-fidelity method for hyperparameter and neural architecture search that combines the strengths of asynchronous Hyperband and Gaussian process-based Bayesian optimization. At the heart of our method is a probabilistic model that can simultaneously reason across hyperparameters and resource levels, and supports decision-making in the presence of pending evaluations. We demonstrate the effectiveness of our method on a wide range of challenging benchmarks, for tabular data, image classification and language modelling, and report substantial speed-ups over current state-of-the-art methods. Our new methods, along with asynchronous baselines, are implemented in a distributed framework which will be open sourced along with this publication.

📄 PDF Abstract BibTeX arXiv:2003.10865

Code (3)

awslabs/syne-tune 공식 구현 pytorch
autogluon/autogluon pytorch
jim-schwoebel/allie pytorch

Tasks

AutoMLBayesian OptimizationHyperparameter Optimizationimage-classificationmodelNeural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid 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 $x$…
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Parallel Hyperparameter Optimization Of Spiking Neural Network

2024-03-01 · Thomas Firmin, Pierre Boulet, El-Ghazali Talbi

Spiking Neural Networks (SNN). SNNs are based on a more biologically inspired approach than usual artificial neural networks. Such models are characterized by complex dynamics between neurons and spikes. These are very s…

Bayesian OptimizationGPUHyperparameter OptimizationNeural Architecture Search

Asynchronous ε-Greedy Bayesian Optimisation

2020-10-15 · George De Ath, Richard M. Everson, Jonathan E. Fieldsend

Batch Bayesian optimisation (BO) is a successful technique for the optimisation of expensive black-box functions. Asynchronous BO can reduce wallclock time by starting a new evaluation as soon as another finishes, thus m…

Bayesian OptimisationThompson Sampling

Multi-objective Asynchronous Successive Halving

2021-06-23 · Robin Schmucker, Michele Donini, Muhammad Bilal Zafar, David Salinas 외

Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-world applications, accuracy is only one…

FairnessHyperparameter OptimizationLanguage ModelingLanguage Modelling+2

Asynchronous Decentralized Bayesian Optimization for Large Scale Hyperparameter Optimization

2022-07-01 · Romain Egele, Isabelle Guyon, Venkatram Vishwanath, Prasanna Balaprakash

Bayesian optimization (BO) is a promising approach for hyperparameter optimization of deep neural networks (DNNs), where each model training can take minutes to hours. In BO, a computationally cheap surrogate model is em…

Bayesian OptimizationComputational EfficiencyHyperparameter Optimization

Neuromorphic Architecture Optimization for Task-Specific Dynamic Learning

2019-06-04 · Sandeep Madireddy, Angel Yanguas-Gil, Prasanna Balaprakash

The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the …

Meta-Learning