paper-with-me

Papers

AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning

2024-01-29 · Vikas Kanaujia, Mathias S. Scheurer, Vipul Arora

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.

📄 PDF Abstract BibTeX arXiv:2401.15948

Code (0)

등록된 구현이 없습니다.

Tasks

Normalising Flows

Methods 이 논문이 사용한 방법론

Metropolis Hastings Metropolis-Hastings is a Markov Chain Monte Carlo (MCMC) algorithm for approximate inference. It allows for sampling from a probability distribution where direct sampling is…

Similar Papers 제목 키워드 기반

Learning to Plan Optimally with Flow-based Motion Planner

2020-10-21 · Tin Lai, Fabio Ramos

Sampling-based motion planning is the predominant paradigm in many real-world robotic applications, but its performance is immensely dependent on the quality of the samples. The majority of traditional planners are ineff…

Motion Planning

Conformalised Conditional Normalising Flows for Joint Prediction Regions in time series

2024-11-26 · Eshant English, Christoph Lippert

Conformal Prediction offers a powerful framework for quantifying uncertainty in machine learning models, enabling the construction of prediction sets with finite-sample validity guarantees. While easily adaptable to non-…

Conformal PredictionNormalising FlowsPredictionTime Series+1

Conditional Density Estimation with Bayesian Normalising Flows

2018-02-14 · Brian L. Trippe, Richard E. Turner

Modeling complex conditional distributions is critical in a variety of settings. Despite a long tradition of research into conditional density estimation, current methods employ either simple parametric forms or are diff…

Density EstimationNormalising Flows

Learning Electron Bunch Distribution along a FEL Beamline by Normalising Flows

2023-02-27 · Anna Willmann, Jurjen Couperus Cabadağ, Yen-Yu Chang, Richard Pausch 외

Understanding and control of Laser-driven Free Electron Lasers remain to be difficult problems that require highly intensive experimental and theoretical research. The gap between simulated and experimentally collected d…

Normalising Flows

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions

2025-10-29 · Naoki Kiyohara, Edward Johns, Yingzhen Li arxiv

Stochastic differential equations (SDEs) are well suited to modelling noisy and irregularly sampled time series found in finance, physics, and machine learning. Traditional approaches require costly numerical solvers to …