EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917243710865408 |
|---|---|
| author | Wang, Hua Lu, Jinghao Zhang, Fan |
| author_facet | Wang, Hua Lu, Jinghao Zhang, Fan |
| contents | Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and exhibit vulnerability to out-of-distribution samples in image-related tasks. Furthermore, these challenges become particularly pronounced in large-scale Web data analysis tasks, which typically involve complex temporal patterns and multimodal features. This complexity substantially increases optimization difficulty, rendering models prone to stagnation at saddle points within high-dimensional parameter spaces. To address these issues, we propose a lightweight Transformer architecture in conjunction with a novel Escape-Explore Optimizer (EEO). The optimizer enhances both exploration and generalization while effectively avoiding sharp minima and saddle-point traps. Experimental results show that, in representative Web data scenarios, our method achieves performance on par with state-of-the-art models across 11 time-series benchmark datasets and the Synapse medical image segmentation task. Moreover, it demonstrates superior generalization and stability, thereby validating its potential as a versatile cross-task foundation model for Web-scale data mining and analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02551 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis Wang, Hua Lu, Jinghao Zhang, Fan Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Transformer-based foundation models have achieved remarkable progress in tasks such as time-series forecasting and image segmentation. However, they frequently suffer from error accumulation in multivariate long-sequence prediction and exhibit vulnerability to out-of-distribution samples in image-related tasks. Furthermore, these challenges become particularly pronounced in large-scale Web data analysis tasks, which typically involve complex temporal patterns and multimodal features. This complexity substantially increases optimization difficulty, rendering models prone to stagnation at saddle points within high-dimensional parameter spaces. To address these issues, we propose a lightweight Transformer architecture in conjunction with a novel Escape-Explore Optimizer (EEO). The optimizer enhances both exploration and generalization while effectively avoiding sharp minima and saddle-point traps. Experimental results show that, in representative Web data scenarios, our method achieves performance on par with state-of-the-art models across 11 time-series benchmark datasets and the Synapse medical image segmentation task. Moreover, it demonstrates superior generalization and stability, thereby validating its potential as a versatile cross-task foundation model for Web-scale data mining and analysis. |
| title | EEO-TFV: Escape-Explore Optimizer for Web-Scale Time-Series Forecasting and Vision Analysis |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.02551 |