paper-with-me

Papers

Resource-Aware Pareto-Optimal Automated Machine Learning Platform

2020-10-30 · Yao Yang, Andrew Nam, Mohamad M. Nasr-Azadani, Teresa Tung

In this study, we introduce a novel platform Resource-Aware AutoML (RA-AutoML) which enables flexible and generalized algorithms to build machine learning models subjected to multiple objectives, as well as resource and hard-ware constraints. RA-AutoML intelligently conducts Hyper-Parameter Search(HPS) as well as Neural Architecture Search (NAS) to build models optimizing predefined objectives. RA-AutoML is a versatile framework that allows user to prescribe many resource/hardware constraints along with objectives demanded by the problem at hand or business requirements. At its core, RA-AutoML relies on our in-house search-engine algorithm,MOBOGA, which combines a modified constraint-aware Bayesian Optimization and Genetic Algorithm to construct Pareto optimal candidates. Our experiments on CIFAR-10 dataset shows very good accuracy compared to results obtained by state-of-art neural network models, while subjected to resource constraints in the form of model size.

📄 PDF Abstract BibTeX arXiv:2011.00073

Code (0)

등록된 구현이 없습니다.

Tasks

AutoMLBayesian OptimizationBIG-bench Machine LearningNeural Architecture Search

Similar Papers 제목 키워드 기반

POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification

2022-12-13 · Andrea Falanti, Eugenio Lomurno, Danilo Ardagna, Matteo Matteucci

The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning …

AutoMLNeural Architecture SearchTime SeriesTime Series Analysis+1

NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space

2026-08-13 · Eleftherios Mylonas, Angelos Kouprizas, Michael Birbas, Alexios Birbas arxiv

Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by hardware-aware Neural Architecture Search (NAS). While recen…

Neural Architecture Search

Online Resource Allocation with Convex-set Machine-Learned Advice

2023-06-21 · Negin Golrezaei, Patrick Jaillet, Zijie Zhou

Decision-makers often have access to a machine-learned prediction about demand, referred to as advice, which can potentially be utilized in online decision-making processes for resource allocation. However, exploiting su…

Decision Making

Pareto-Frontier-aware Neural Architecture Search

2021-01-01 · Yong Guo, Yaofo Chen, Yin Zheng, Peilin Zhao 외

Designing feasible and effective architectures is essential for deploying deep models to real-world scenarios. In practice, one has to consider multiple objectives (e.g., model performance and computational cost) and div…

CPUGPUNeural Architecture Search

IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning

2021-02-16 · Nan Wu, Yuan Xie, Cong Hao

Despite the great success of High-Level Synthesis (HLS) tools, we observe several unresolved challenges: 1) the high-level abstraction of programming styles in HLS sometimes conceals optimization opportunities; 2) existi…

Graph Neural NetworkHigh-Level SynthesisReinforcement Learning (RL)