TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.16.5.132
TI  - AdvNF: Reducing mode collapse in conditional normalising flows using adversarial learning
PY  - 2024/05/24
UR  - https://scipost.org/SciPostPhys.16.5.132
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 16
IS  - 5
SP  - 132
A1  - Kanaujia, Vikas
AU  - Scheurer, Mathias S.
AU  - Arora, Vipul
AB  - 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.
ER  -

@Article{10.21468/SciPostPhys.16.5.132,
	title={{AdvNF: Reducing mode collapse in conditional normalising flows using adversarial learning}},
	author={Vikas Kanaujia and Mathias S. Scheurer and Vipul Arora},
	journal={SciPost Phys.},
	volume={16},
	pages={132},
	year={2024},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.16.5.132},
	url={https://scipost.org/10.21468/SciPostPhys.16.5.132},
}