Kernelised Normalising Flows

• URL: http://arxiv.org/abs/2307.14839v4
• Date: Thu, 27 Jun 2024 04:58:29 GMT
• Title: Kernelised Normalising Flows
• Authors: Eshant English, Matthias Kirchler, Christoph Lippert,
• Abstract summary: Normalising Flows are non-parametric statistical models characterised by their dual capabilities of density estimation and generation. We present Ferumal flow, a novel kernelised normalising flow paradigm that integrates kernels into the framework.
• Score: 10.31916245015817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Using Parametric PINNs for Predicting Internal and External Turbulent Flows [6.387263468033964]
  We build upon the previously proposed RANS-PINN framework, which only focused on predicting flow over a cylinder. We investigate its accuracy in predicting relevant turbulent flow variables for both internal and external flows.
  arXiv  Detail & Related papers  (2024-10-24T17:08:20Z)
• Guided Flows for Generative Modeling and Decision Making [55.42634941614435]
  We show that Guided Flows significantly improves the sample quality in conditional image generation and zero-shot text synthesis-to-speech. Notably, we are first to apply flow models for plan generation in the offline reinforcement learning setting ax speedup in compared to diffusion models.
  arXiv  Detail & Related papers  (2023-11-22T15:07:59Z)
• Free-form Flows: Make Any Architecture a Normalizing Flow [8.163244519983298]
  We develop a training procedure that uses an efficient estimator for the gradient of the change of variables formula. This enables any dimension-preserving neural network to serve as a generative model through maximum likelihood training. We achieve excellent results in molecule generation benchmarks utilizing $E(n)$-equivariant networks.
  arXiv  Detail & Related papers  (2023-10-25T13:23:08Z)
• Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model [6.705438773768439]
  Uncertainty quantification (UQ) of subsurface two-phase flow usually requires numerous executions of forward simulations under varying conditions. In this work, a novel coupled theory-guided neural network (TgNN) based surrogate model is built to facilitate efficiency under the premise of satisfactory accuracy.
  arXiv  Detail & Related papers  (2022-05-28T02:33:46Z)
• GMFlow: Learning Optical Flow via Global Matching [124.57850500778277]
  We propose a GMFlow framework for learning optical flow estimation. It consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation. Our new framework outperforms 32-iteration RAFT's performance on the challenging Sintel benchmark.
  arXiv  Detail & Related papers  (2021-11-26T18:59:56Z)
• Sparse Flows: Pruning Continuous-depth Models [107.98191032466544]
  We show that pruning improves generalization for neural ODEs in generative modeling. We also show that pruning finds minimal and efficient neural ODE representations with up to 98% less parameters compared to the original network, without loss of accuracy.
  arXiv  Detail & Related papers  (2021-06-24T01:40:17Z)
• Generative Flows with Invertible Attentions [135.23766216657745]
  We introduce two types of invertible attention mechanisms for generative flow models. We exploit split-based attention mechanisms to learn the attention weights and input representations on every two splits of flow feature maps. Our method provides invertible attention modules with tractable Jacobian determinants, enabling seamless integration of it at any positions of the flow-based models.
  arXiv  Detail & Related papers  (2021-06-07T20:43:04Z)
• An Ode to an ODE [78.97367880223254]
  We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the group O(d) This nested system of two flows provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem.
  arXiv  Detail & Related papers  (2020-06-19T22:05:19Z)
• NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity [28.201670958962453]
  Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages.
  arXiv  Detail & Related papers  (2020-06-11T09:35:00Z)
• Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows [40.9137348900942]
  We propose a novel type of flow driven by a differential deformation of the Wiener process. As a result, we obtain a rich time series model whose observable process inherits many of the appealing properties of its base process.
  arXiv  Detail & Related papers  (2020-02-24T20:13:43Z)
• Learning Likelihoods with Conditional Normalizing Flows [54.60456010771409]
  Conditional normalizing flows (CNFs) are efficient in sampling and inference. We present a study of CNFs where the base density to output space mapping is conditioned on an input x, to model conditional densities p(y|x)
  arXiv  Detail & Related papers  (2019-11-29T19:17:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.