Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.15948 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914814532517888 |
|---|---|
| author | Kanaujia, Vikas Scheurer, Mathias S. Arora, Vipul |
| author_facet | Kanaujia, Vikas Scheurer, Mathias S. Arora, Vipul |
| contents | Deep generative models complement Markov-chain-Monte-Carlo methods for efficiently sampling from high-dimensional distributions. Among these methods, explicit generators, such as Normalising Flows (NFs), in combination with the Metropolis Hastings algorithm have been extensively applied to get unbiased samples from target distributions. We systematically study central problems in conditional NFs, such as high variance, mode collapse and data efficiency. We propose adversarial training for NFs to ameliorate these problems. Experiments are conducted with low-dimensional synthetic datasets and XY spin models in two spatial dimensions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15948 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning Kanaujia, Vikas Scheurer, Mathias S. Arora, Vipul Machine Learning Statistical Mechanics Computational Physics Deep generative models complement Markov-chain-Monte-Carlo methods for efficiently sampling from high-dimensional distributions. Among these methods, explicit generators, such as Normalising Flows (NFs), in combination with the Metropolis Hastings algorithm have been extensively applied to get unbiased samples from target distributions. We systematically study central problems in conditional NFs, such as high variance, mode collapse and data efficiency. We propose adversarial training for NFs to ameliorate these problems. Experiments are conducted with low-dimensional synthetic datasets and XY spin models in two spatial dimensions. |
| title | AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning |
| topic | Machine Learning Statistical Mechanics Computational Physics |
| url | https://arxiv.org/abs/2401.15948 |