Papers Normalising Flows
“Normalising Flows” 태그가 달린 논문 49편 · 필터 해제
JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows
Conformal prediction provides a model-agnostic framework for uncertainty quantification with finite-sample validity guarantees, making it an attractive tool for constructing reliable prediction sets. However, existing ap…
Conformal PredictionNormalising FlowsPredictionUncertainty QuantificationCommunicating Likelihoods with Normalising Flows
We present a machine-learning-based workflow to model an unbinned likelihood from its samples. A key advancement over existing approaches is the validation of the learned likelihood using rigorous statistical tests of th…
Normalising 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+1Marginal Causal Flows for Validation and Inference
Investigating the marginal causal effect of an intervention on an outcome from complex data remains challenging due to the inflexibility of employed models and the lack of complexity in causal benchmark datasets, which o…
Normalising Flows$\mathtt{emuflow}$: Normalising Flows for Joint Cosmological Analysis
Given the growth in the variety and precision of astronomical datasets of interest for cosmology, the best cosmological constraints are invariably obtained by combining data from different experiments. At the likelihood …
Normalising FlowsLinear combinations of latents in generative models: subspaces and beyond
Sampling from generative models has become a crucial tool for applications like data synthesis and augmentation. Diffusion, Flow Matching and Continuous Normalising Flows have shown effectiveness across various modalitie…
Experimental DesignNormalising FlowsNormalizing Flow-based Differentiable Particle Filters
Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear no…
Density EstimationNormalising FlowsState EstimationState Space Models+1AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning
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 w…
Normalising FlowsFlexible Tails for Normalising Flows, with Application to the Modelling of Financial Return Data
We propose a transformation capable of altering the tail properties of a distribution, motivated by extreme value theory, which can be used as a layer in a normalizing flow to approximate multivariate heavy tailed distri…
Normalising FlowsMixerFlow: MLP-Mixer meets Normalising Flows
Normalising flows are generative models that transform a complex density into a simpler density through the use of bijective transformations enabling both density estimation and data generation from a single model. %Howe…
Density EstimationKolmogorov-Arnold NetworksNormalising FlowsProbabilistic Classification by Density Estimation Using Gaussian Mixture Model and Masked Autoregressive Flow
Density estimation, which estimates the distribution of data, is an important category of probabilistic machine learning. A family of density estimators is mixture models, such as Gaussian Mixture Model (GMM) by expectat…
ClassificationDensity EstimationNormalising FlowsTestable Likelihoods for Beyond-the-Standard Model Fits
Studying potential BSM effects at the precision frontier requires accurate transfer of information from low-energy measurements to high-energy BSM models. We propose to use normalising flows to construct likelihood funct…
FormmodelNormalising FlowsLInKs "Lifting Independent Keypoints" -- Partial Pose Lifting for Occlusion Handling with Improved Accuracy in 2D-3D Human Pose Estimation
We present LInKs, a novel unsupervised learning method to recover 3D human poses from 2D kinematic skeletons obtained from a single image, even when occlusions are present. Our approach follows a unique two-step process,…
3D Human Pose EstimationAttributeDimensionality ReductionNormalising Flows+3Bayesian Exploration Networks
Bayesian reinforcement learning (RL) offers a principled and elegant approach for sequential decision making under uncertainty. Most notably, Bayesian agents do not face an exploration/exploitation dilemma, a major patho…
Decision MakingDecision Making Under UncertaintyDensity EstimationNormalising Flows+3Kernelised 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…
Density EstimationNormalising FlowsNEnv: Neural Environment Maps for Global Illumination
Environment maps are commonly used to represent and compute far-field illumination in virtual scenes. However, they are expensive to evaluate and sample from, limiting their applicability to real-time rendering. Previous…
Neural RenderingNormalising FlowsDecorrelation using Optimal Transport
Being able to decorrelate a feature space from protected attributes is an area of active research and study in ethics, fairness, and also natural sciences. We introduce a novel decorrelation method using Convex Neural Op…
Binary ClassificationEthicsFairnessNormalising FlowsA Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
The generation of virtual populations (VPs) of anatomy is essential for conducting in silico trials of medical devices. Typically, the generated VP should capture sufficient variability while remaining plausible and shou…
AnatomyNormalising FlowsSpecificityHuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation
Monocular 3D human pose and shape estimation is an ill-posed problem since multiple 3D solutions can explain a 2D image of a subject. Recent approaches predict a probability distribution over plausible 3D pose and shape …
3D human pose and shape estimation3D Human Pose EstimationDiversityMulti-Hypotheses 3D Human Pose Estimation+1Learning Electron Bunch Distribution along a FEL Beamline by Normalising Flows
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