Predator-Prey Model: Driven Hunt for Accelerated Grokking
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914035538067456 |
|---|---|
| author | Lopatin, I. A. Kozyrev, S. V. Pechen, A. N. |
| author_facet | Lopatin, I. A. Kozyrev, S. V. Pechen, A. N. |
| contents | A machine learning method is proposed using two agents that simulate the biological behavior of a predator and a prey. In this method, the predator and the prey interact with each other - the predator chases the prey while the prey runs away from the predator - to perform an optimization on the landscape. This method allows, for the case of a ravine landscape (i.e., a landscape with narrow ravines and with gentle slopes along the ravines) to avoid getting optimization stuck in the ravine. For this, in the optimization over a ravine landscape the predator drives the prey along the ravine. Thus we also call this approach, for the case of ravine landscapes, the driven hunt method. For some examples of grokking (i.e., delayed generalization) problems we show that this method allows for achieving up to a hundred times faster learning compared to the standard learning procedure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10562 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predator-Prey Model: Driven Hunt for Accelerated Grokking Lopatin, I. A. Kozyrev, S. V. Pechen, A. N. Neural and Evolutionary Computing Adaptation and Self-Organizing Systems A machine learning method is proposed using two agents that simulate the biological behavior of a predator and a prey. In this method, the predator and the prey interact with each other - the predator chases the prey while the prey runs away from the predator - to perform an optimization on the landscape. This method allows, for the case of a ravine landscape (i.e., a landscape with narrow ravines and with gentle slopes along the ravines) to avoid getting optimization stuck in the ravine. For this, in the optimization over a ravine landscape the predator drives the prey along the ravine. Thus we also call this approach, for the case of ravine landscapes, the driven hunt method. For some examples of grokking (i.e., delayed generalization) problems we show that this method allows for achieving up to a hundred times faster learning compared to the standard learning procedure. |
| title | Predator-Prey Model: Driven Hunt for Accelerated Grokking |
| topic | Neural and Evolutionary Computing Adaptation and Self-Organizing Systems |
| url | https://arxiv.org/abs/2509.10562 |