Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2409.05258 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909308750397440 |
|---|---|
| author | Ardeshir, Shervin |
| author_facet | Ardeshir, Shervin |
| contents | This paper explores a top-down approach to automating incremental advances in machine learning research through component-level innovation, facilitated by Large Language Models (LLMs). Our framework systematically generates novel components, validates their feasibility, and evaluates their performance against existing baselines. A key distinction of this approach lies in how these novel components are generated. Unlike traditional AutoML and NAS methods, which often rely on a bottom-up combinatorial search over predefined, hardcoded base components, our method leverages the cross-domain knowledge embedded in LLMs to propose new components that may not be confined to any hard-coded predefined set. By incorporating a reward model to prioritize promising hypotheses, we aim to improve the efficiency of the hypothesis generation and evaluation process. We hope this approach offers a new avenue for exploration and contributes to the ongoing dialogue in the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05258 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Automated Machine Learning Research Ardeshir, Shervin Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition This paper explores a top-down approach to automating incremental advances in machine learning research through component-level innovation, facilitated by Large Language Models (LLMs). Our framework systematically generates novel components, validates their feasibility, and evaluates their performance against existing baselines. A key distinction of this approach lies in how these novel components are generated. Unlike traditional AutoML and NAS methods, which often rely on a bottom-up combinatorial search over predefined, hardcoded base components, our method leverages the cross-domain knowledge embedded in LLMs to propose new components that may not be confined to any hard-coded predefined set. By incorporating a reward model to prioritize promising hypotheses, we aim to improve the efficiency of the hypothesis generation and evaluation process. We hope this approach offers a new avenue for exploration and contributes to the ongoing dialogue in the field. |
| title | Towards Automated Machine Learning Research |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.05258 |