Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.09566 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911202794274816 |
|---|---|
| author | Revin, Ilia Strelkov, Leon Potemkin, Vadim A. Kireev, Ivan Savchenko, Andrey |
| author_facet | Revin, Ilia Strelkov, Leon Potemkin, Vadim A. Kireev, Ivan Savchenko, Andrey |
| contents | There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Automated Evolutionary Optimization for Resource-Efficient Neural Network Training Revin, Ilia Strelkov, Leon Potemkin, Vadim A. Kireev, Ivan Savchenko, Andrey Machine Learning There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary optimization to model architecture and training strategy. PETRA includes pruning, quantization, and loss regularization. Experimental studies on real-world data with financial event sequences, as well as image and time-series -- benchmarks, demonstrate PETRA's ability to improve neural model performance and scalability -- namely, a significant decrease in model size (up to 75%) and latency (up to 33%), and an increase in throughput (by 13%) without noticeable degradation in the target metric. |
| title | Automated Evolutionary Optimization for Resource-Efficient Neural Network Training |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.09566 |