Kernelised Normalising Flows
Normalising Flows are non-parametric statistical models characterised by their dual capabilities of density estimation and generation. This duality requires an inherently invertible architecture. However, the requirement of invertibility imposes constraints on their expressiveness, necessitating a large number of parameters and innovative architectural designs to achieve good results. Whilst flow-based models predominantly rely on neural-network-based transformations for expressive designs, alternative transformation methods have received limited attention. In this work, we present Ferumal flow, a novel kernelised normalising flow paradigm that integrates kernels into the framework. Our results demonstrate that a kernelised flow can yield competitive or superior results compared to neural network-based flows whilst maintaining parameter efficiency. Kernelised flows excel especially in the low-data regime, enabling flexible non-parametric density estimation in applications with sparse data availability.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationNormalising FlowsSimilar Papers 제목 키워드 기반
Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
We show that normalising flows become pathological when used to model targets whose supports have complicated topologies. In this scenario, we prove that a flow must become arbitrarily numerically noninvertible in order …
Density EstimationNormalising FlowsConformalised Conditional Normalising Flows for Joint Prediction Regions in time series
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+1Sinusoidal Flow: A Fast Invertible Autoregressive Flow
Normalising flows offer a flexible way of modelling continuous probability distributions. We consider expressiveness, fast inversion and exact Jacobian determinant as three desirable properties a normalising flow should …
Normalising FlowsOn the relationship between Normalising Flows and Variational- and Denoising Autoencoders
Normalising Flows (NFs) are a class of likelihood-based generative models that have recently gained popularity. They are based on the idea of transforming a simple density into that of the data. We seek to better underst…
DenoisingNormalising FlowsRepresentation LearningText-free non-parallel many-to-many voice conversion using normalising flows
Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speec…
Normalising FlowsSpeech Synthesistext-to-speechText to Speech+2