paper-with-me

Papers

BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

2019-10-25 · Colin White, Willie Neiswanger, Yash Savani

Over the past half-decade, many methods have been considered for neural architecture search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter optimization, has recently emerged as a very promising strategy for NAS when it is coupled with a neural predictor. Recent work has proposed different instantiations of this framework, for example, using Bayesian neural networks or graph convolutional networks as the predictive model within BO. However, the analyses in these papers often focus on the full-fledged NAS algorithm, so it is difficult to tell which individual components of the framework lead to the best performance. In this work, we give a thorough analysis of the "BO + neural predictor" framework by identifying five main components: the architecture encoding, neural predictor, uncertainty calibration method, acquisition function, and acquisition optimization strategy. We test several different methods for each component and also develop a novel path-based encoding scheme for neural architectures, which we show theoretically and empirically scales better than other encodings. Using all of our analyses, we develop a final algorithm called BANANAS, which achieves state-of-the-art performance on NAS search spaces. We adhere to the NAS research checklist (Lindauer and Hutter 2019) to facilitate best practices, and our code is available at https://github.com/naszilla/naszilla.

📄 PDF Abstract BibTeX arXiv:1910.11858

Code (3)

naszilla/bananas 공식 구현 tf
naszilla/naszilla 공식 구현 tf
ZachZhu7/banana-git tf

Tasks

Bayesian OptimizationHyperparameter OptimizationNeural Architecture SearchReinforcement Learning

Methods 이 논문이 사용한 방법론

Test 설명 없음
Graph Convolutional Networks 설명 없음
Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

Mutation is all you need

2021-07-04 · ICML Workshop AutoML 2021 7 · Lennart Schneider, Florian Pfisterer, Martin Binder, Bernd Bischl

Neural architecture search (NAS) promises to make deep learning accessible to non-experts by automating architecture engineering of deep neural networks. BANANAS is one state-of-the-art NAS method that is embedded within…

AllBayesian OptimizationNeural Architecture Search

BANANAS: Bayesian Optimization with Neural Networks for Neural Architecture Search

2019-09-25 · Colin White, Willie Neiswanger, Yash Savani

Neural Architecture Search (NAS) has seen an explosion of research in the past few years. A variety of methods have been proposed to perform NAS, including reinforcement learning, Bayesian optimization with a Gaussian pr…

Bayesian OptimizationNeural Architecture Searchreinforcement-learningReinforcement Learning (RL)

Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces

2014-09-14 · Kevin Swersky, David Duvenaud, Jasper Snoek, Frank Hutter 외

In practical Bayesian optimization, we must often search over structures with differing numbers of parameters. For instance, we may wish to search over neural network architectures with an unknown number of layers. To re…

Bayesian Optimization

Deep Neural Architecture Search with Deep Graph Bayesian Optimization

2019-05-14 · Lizheng Ma, Jiaxu Cui, Bo Yang

Bayesian optimization (BO) is an effective method of finding the global optima of black-box functions. Recently BO has been applied to neural architecture search and shows better performance than pure evolutionary strate…

Bayesian OptimizationGaussian ProcessesGraph Neural NetworkNeural Architecture Search

Bayesian Neural Architecture Search using A Training-Free Performance Metric

2020-01-29 · Andrés Camero, Hao Wang, Enrique Alba, Thomas Bäck

Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNN…

Bayesian OptimizationNeural Architecture SearchTime SeriesTime Series Analysis+1