paper-with-me

홈 › Papers

Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search

2022-01-24 · Yao Shu, Zhongxiang Dai, Zhaoxuan Wu, Bryan Kian Hsiang Low

Neural architecture search (NAS) has gained immense popularity owing to its ability to automate neural architecture design. A number of training-free metrics are recently proposed to realize NAS without training, hence making NAS more scalable. Despite their competitive empirical performances, a unified theoretical understanding of these training-free metrics is lacking. As a consequence, (a) the relationships among these metrics are unclear, (b) there is no theoretical interpretation for their empirical performances, and (c) there may exist untapped potential in existing training-free NAS, which probably can be unveiled through a unified theoretical understanding. To this end, this paper presents a unified theoretical analysis of gradient-based training-free NAS, which allows us to (a) theoretically study their relationships, (b) theoretically guarantee their generalization performances, and (c) exploit our unified theoretical understanding to develop a novel framework named hybrid NAS (HNAS) which consistently boosts training-free NAS in a principled way. Remarkably, HNAS can enjoy the advantages of both training-free (i.e., the superior search efficiency) and training-based (i.e., the remarkable search effectiveness) NAS, which we have demonstrated through extensive experiments.

📄 PDF Abstract BibTeX arXiv:2201.09785

Code (1)

shuyao95/HNAS 공식 구현 pytorch

Tasks

Neural Architecture Search

Similar Papers 제목 키워드 기반

Efficient logic architecture in training gradient boosting decision tree for high-performance and edge computing

2018-12-20 · Takuya Tanaka, Ryosuke Kasahara, Daishiro Kobayashi

This study proposes a logic architecture for the high-speed and power efficiently training of a gradient boosting decision tree model of binary classification. We implemented the proposed logic architecture on an FPGA an…

Binary ClassificationCPUEdge-computingGeneral Classification+1

Generalization Properties of NAS under Activation and Skip Connection Search

2022-09-15 · Zhenyu Zhu, Fanghui Liu, Grigorios G Chrysos, Volkan Cevher

Neural Architecture Search (NAS) has fostered the automatic discovery of state-of-the-art neural architectures. Despite the progress achieved with NAS, so far there is little attention to theoretical guarantees on NAS. I…

Learning TheoryNeural Architecture Search

TF Boosted Trees: A scalable TensorFlow based framework for gradient boosting

2017-10-31 · Natalia Ponomareva, Soroush Radpour, Gilbert Hendry, Salem Haykal 외

TF Boosted Trees (TFBT) is a new open-sourced frame-work for the distributed training of gradient boosted trees. It is based on TensorFlow, and its distinguishing features include a novel architecture, automatic loss dif…

Robustifying and Boosting Training-Free Neural Architecture Search

2024-03-12 · Zhenfeng He, Yao Shu, Zhongxiang Dai, Bryan Kian Hsiang Low

Neural architecture search (NAS) has become a key component of AutoML and a standard tool to automate the design of deep neural networks. Recently, training-free NAS as an emerging paradigm has successfully reduced the s…

AutoMLBayesian OptimizationNeural Architecture Search

A generalized decision tree ensemble based on the NeuralNetworks architecture: Distributed Gradient Boosting Forest (DGBF)

2024-02-04 · Ángel Delgado-Panadero, José Alberto Benítez-Andrades, María Teresa García-Ordás

Tree ensemble algorithms as RandomForest and GradientBoosting are currently the dominant methods for modeling discrete or tabular data, however, they are unable to perform a hierarchical representation learning from raw …

Representation Learning