Additive regularization schedule for neural architecture search
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913397349548032 |
|---|---|
| author | Potanin, Mark Vayser, Kirill Strijov, Vadim |
| author_facet | Potanin, Mark Vayser, Kirill Strijov, Vadim |
| contents | Neural network structures have a critical impact on the accuracy and stability of forecasting. Neural architecture search procedures help design an optimal neural network according to some loss function, which represents a set of quality criteria. This paper investigates the problem of neural network structure optimization. It proposes a way to construct a loss function, which contains a set of additive elements. Each element is called the regularizer. It corresponds to some part of the neural network structure and represents a criterion to optimize. The optimization procedure changes the structure in iterations. To optimize various parts of the structure, the procedure changes the set of regularizers according to some schedule. The authors propose a way to construct the additive regularization schedule. By comparing regularized models with non-regularized ones for a collection of datasets the computational experiments show that the proposed method finds efficient neural network structure and delivers accurate networks of low complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12992 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Additive regularization schedule for neural architecture search Potanin, Mark Vayser, Kirill Strijov, Vadim Machine Learning Neural network structures have a critical impact on the accuracy and stability of forecasting. Neural architecture search procedures help design an optimal neural network according to some loss function, which represents a set of quality criteria. This paper investigates the problem of neural network structure optimization. It proposes a way to construct a loss function, which contains a set of additive elements. Each element is called the regularizer. It corresponds to some part of the neural network structure and represents a criterion to optimize. The optimization procedure changes the structure in iterations. To optimize various parts of the structure, the procedure changes the set of regularizers according to some schedule. The authors propose a way to construct the additive regularization schedule. By comparing regularized models with non-regularized ones for a collection of datasets the computational experiments show that the proposed method finds efficient neural network structure and delivers accurate networks of low complexity. |
| title | Additive regularization schedule for neural architecture search |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.12992 |