paper-with-me

Papers

ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces

2021-01-19 · Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Qiuyi Zhang, Daiyi Peng, Deepali Jain, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Yuxiang Yang

In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate that previous evolutionary algorithms which rely on mutation-based approaches, while flexible over combinatorial spaces, suffer from a curse of dimensionality in high dimensional continuous spaces both theoretically and empirically, which thus limits their scope over hybrid search spaces as well. In order to combat this curse, we propose ES-ENAS, a simple and modular joint optimization procedure combining the class of sample-efficient smoothed gradient techniques, commonly known as Evolutionary Strategies (ES), with combinatorial optimizers in a highly scalable and intuitive way, inspired by the one-shot or supernet paradigm introduced in Efficient Neural Architecture Search (ENAS). By doing so, we achieve significantly more sample efficiency, which we empirically demonstrate over synthetic benchmarks, and are further able to apply ES-ENAS for architecture search over popular RL benchmarks.

📄 PDF Abstract BibTeX arXiv:2101.07415

Code (2)

google-research/google-research 공식 구현 tf
code-implementation1/Code1/tree/main/EF-ENAS mindspore

Tasks

Combinatorial OptimizationContinuous ControlEvolutionary AlgorithmsMultiobjective OptimizationNeural Architecture SearchQuantization

Similar Papers 제목 키워드 기반

NPENAS: Neural Predictor Guided Evolution for Neural Architecture Search

2020-03-28 · Chen Wei, Chuang Niu, Yiping Tang, Yue Wang 외

Neural architecture search (NAS) is a promising method for automatically design neural architectures. NAS adopts a search strategy to explore the predefined search space to find outstanding performance architecture with …

Bayesian OptimizationEvolutionary AlgorithmsNeural Architecture Search

Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search

2020-03-07 · Haoyu Zhang, Yaochu Jin, Ran Cheng, Kuangrong Hao

The performance of a deep neural network is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary ne…

Evolutionary Algorithmsglobal-optimizationNeural Architecture Search

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

2022-12-01 · IEEE Transactions on Evolutionary Computation 2022 12 · Xiangning Xie; Yuqiao Liu; Yanan Sun; Gary G. Yen; Bing Xue; Mengjie Zhang

Neural architecture search (NAS), which automatically designs the architectures of deep neural networks, has achieved breakthrough success over many applications in the past few years. Among different classes of NAS meth…

BenchmarkingGPUNeural Architecture Search

BenchENAS: A Benchmarking Platform for Evolutionary Neural Architecture Search

2021-08-09 · Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen 외

Neural architecture search (NAS), which automatically designs the architectures of deep neural networks, has achieved breakthrough success over many applications in the past few years. Among different classes of NAS meth…

BenchmarkingGPUNeural Architecture Search

Evolutionary Neural Architecture Search with Dual Contrastive Learning

2025-12-23 · Xian-Rong Zhang, Yue-Jiao Gong, Wei-Neng Chen, Jun Zhang arxiv

Evolutionary Neural Architecture Search (ENAS) has gained attention for automatically designing neural network architectures. Recent studies use a neural predictor to guide the process, but the high computational costs o…

Neural Architecture SearchSelf-Supervised LearningContrastive Learning