VINA: Variational Invertible Neural Architectures
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_ | 1866917290872668160 |
|---|---|
| author | Shekhar, Shubhanshu Khojasteh, Mohammad Javad Acharya, Ananya Tohme, Tony Youcef-Toumi, Kamal |
| author_facet | Shekhar, Shubhanshu Khojasteh, Mohammad Javad Acharya, Ananya Tohme, Tony Youcef-Toumi, Kamal |
| contents | The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural networks (INNs) build on these principles to address supervised inverse problems, enabling direct modeling of both forward and inverse mappings. In this paper, we revisit these architectures from both theoretical and practical perspectives and address a key gap in the literature: the lack of theoretical guarantees on approximation quality under realistic assumptions, whether for posterior inference in INNs or for generative modeling with NFs.
We introduce a unified framework for INNs and NFs based on variational unsupervised loss functions, inspired by analogous formulations in related areas such as generative adversarial networks (GANs) and the Precision-Recall divergence for training normalizing flows. Within this framework, we derive theoretical performance guarantees, quantifying posterior accuracy for INNs and distributional accuracy for NFs, under assumptions that are weaker and more practically realistic than those used in prior work.
Building on these theoretical results, we conduct extensive case studies to distill general design principles and practical guidelines. We conclude by demonstrating the effectiveness of our approach on a realistic ocean-acoustic inversion problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20480 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VINA: Variational Invertible Neural Architectures Shekhar, Shubhanshu Khojasteh, Mohammad Javad Acharya, Ananya Tohme, Tony Youcef-Toumi, Kamal Machine Learning Artificial Intelligence The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural networks (INNs) build on these principles to address supervised inverse problems, enabling direct modeling of both forward and inverse mappings. In this paper, we revisit these architectures from both theoretical and practical perspectives and address a key gap in the literature: the lack of theoretical guarantees on approximation quality under realistic assumptions, whether for posterior inference in INNs or for generative modeling with NFs. We introduce a unified framework for INNs and NFs based on variational unsupervised loss functions, inspired by analogous formulations in related areas such as generative adversarial networks (GANs) and the Precision-Recall divergence for training normalizing flows. Within this framework, we derive theoretical performance guarantees, quantifying posterior accuracy for INNs and distributional accuracy for NFs, under assumptions that are weaker and more practically realistic than those used in prior work. Building on these theoretical results, we conduct extensive case studies to distill general design principles and practical guidelines. We conclude by demonstrating the effectiveness of our approach on a realistic ocean-acoustic inversion problem. |
| title | VINA: Variational Invertible Neural Architectures |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2602.20480 |