Proceedings of the International Conference on Computer-Aided Design 2018
DOI: 10.1145/3240765.3243494
|View full text |Cite
|
Sign up to set email alerts
|

Searching toward pareto-optimal device-aware neural architectures

Abstract: Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
19
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 28 publications
(19 citation statements)
references
References 35 publications
0
19
0
Order By: Relevance
“…By default, both Auto-WEKA and AutoSklearn optimize for only one metric, such as the error rate or accuracy. MONAS and DPP-Net [36], on the other hand, are natural extensions that search and optimize for multiple device-agnostic and device-aware constraints, resulting in gradually better models for all optimization objectives. The outcome of this process are tuples of objective performances where we can select the ones that are Pareto-optimal, that is they are optimal at least in one of the objectives.…”
Section: Binary Classification With Traditional Machine Learning Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…By default, both Auto-WEKA and AutoSklearn optimize for only one metric, such as the error rate or accuracy. MONAS and DPP-Net [36], on the other hand, are natural extensions that search and optimize for multiple device-agnostic and device-aware constraints, resulting in gradually better models for all optimization objectives. The outcome of this process are tuples of objective performances where we can select the ones that are Pareto-optimal, that is they are optimal at least in one of the objectives.…”
Section: Binary Classification With Traditional Machine Learning Methodsmentioning
confidence: 99%
“…Similar to MONAS, it optimizes device-related (e.g., memory usage) and device-agnostic (e.g., accuracy or model size) objectives. Both approaches were evaluated in [36], showing that both frameworks are effective and are able to achieves Pareto-optimality with respect to the given objectives. While both resource-aware optimization frameworks are closely related to the objectives of our research, an open source implementation for MONAS and DPP-Net was not available for evaluation and adaptation purposes.…”
Section: Related Workmentioning
confidence: 99%
“…Neural Architecture Search (NAS) [26] is an emerging approach in which pruning and quantization get embedded into a global search where also the topological parameters of the ConvNet, e.g. number of layers, number of filters, connections between layers, etc., take part to the objective function,…”
Section: Neural Architecture Searchmentioning
confidence: 99%
“…ConvNets are computing-and memory-intensive models that need aggressive compression to fit low-power CPUs. Along with custom compression pipelines based on quantization [4], pruning [5] and neural architecture search [6], a common trend today is to offer end-users a portfolio of pre-trained models with the same back-bone topology but variable size and hence, a different latency-accuracy trade-off [7][8][9][10][11]. One can pick the implementation that best fits the available computing architecture and the application requirements, therefore reducing the design time.…”
Section: Introductionmentioning
confidence: 99%