Consistent estimation of generative model representations in the data kernel perspective space
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_ | 1866912191455690752 |
|---|---|
| author | Acharyya, Aranyak Trosset, Michael W. Priebe, Carey E. Helm, Hayden S. |
| author_facet | Acharyya, Aranyak Trosset, Michael W. Priebe, Carey E. Helm, Hayden S. |
| contents | Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of generative models evolves, it is important to develop techniques to study and analyze differences in model behaviour. In this paper we present novel theoretical results for embedding-based representations of generative models in the context of a set of queries. In particular, we establish sufficient conditions for the consistent estimation of the model embeddings in situations where the query set and the number of models grow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17308 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Consistent estimation of generative model representations in the data kernel perspective space Acharyya, Aranyak Trosset, Michael W. Priebe, Carey E. Helm, Hayden S. Machine Learning Statistics Theory Generative models, such as large language models and text-to-image diffusion models, produce relevant information when presented a query. Different models may produce different information when presented the same query. As the landscape of generative models evolves, it is important to develop techniques to study and analyze differences in model behaviour. In this paper we present novel theoretical results for embedding-based representations of generative models in the context of a set of queries. In particular, we establish sufficient conditions for the consistent estimation of the model embeddings in situations where the query set and the number of models grow. |
| title | Consistent estimation of generative model representations in the data kernel perspective space |
| topic | Machine Learning Statistics Theory |
| url | https://arxiv.org/abs/2409.17308 |