NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity

• URL: http://arxiv.org/abs/2006.06280v4
• Date: Fri, 23 Oct 2020 03:36:10 GMT
• Title: NanoFlow: Scalable Normalizing Flows with Sublinear Parameter Complexity
• Authors: Sang-gil Lee, Sungwon Kim, Sungroh Yoon
• Abstract summary: 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.
• Score: 28.201670958962453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Normalizing flows (NFs) have become a prominent method for deep generative models that allow for an analytic probability density estimation and efficient synthesis. However, a flow-based network is considered to be inefficient in parameter complexity because of reduced expressiveness of bijective mapping, which renders the models unfeasibly expensive in terms of parameters. We present an alternative parameterization scheme called NanoFlow, which uses a single neural density estimator to model multiple transformation stages. Hence, we propose an efficient parameter decomposition method and the concept of flow indication embedding, which are key missing components that enable density estimation from a single neural network. Experiments performed on audio and image models confirm that our method provides a new parameter-efficient solution for scalable NFs with significant sublinear parameter complexity.

Related papers

• Dynamical Measure Transport and Neural PDE Solvers for Sampling [77.38204731939273]
  We tackle the task of sampling from a probability density as transporting a tractable density function to the target. We employ physics-informed neural networks (PINNs) to approximate the respective partial differential equations (PDEs) solutions. PINNs allow for simulation- and discretization-free optimization and can be trained very efficiently.
  arXiv  Detail & Related papers  (2024-07-10T17:39:50Z)
• Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations [34.500484733973536]
  Ordinary differential equations (ODEs) are widely used to describe dynamical systems in science, but identifying parameters that explain experimental measurements is challenging. We propose diffusion tempering, a novel regularization technique for probabilistic numerical methods which improves convergence of gradient-based parameter optimization in ODEs. We demonstrate that our method is effective for dynamical systems of different complexity and show that it obtains reliable parameter estimates for a Hodgkin-Huxley model with a practically relevant number of parameters.
  arXiv  Detail & Related papers  (2024-02-19T15:36:36Z)
• Kernelised Normalising Flows [10.31916245015817]
  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.
  arXiv  Detail & Related papers  (2023-07-27T13:18:52Z)
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
  We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT) We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity. In addition, we show that our approach enables us to explore more complex neural-based wave functions.
  arXiv  Detail & Related papers  (2023-03-01T10:38:10Z)
• Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions [0.0]
  This work presents a data-driven, non-intrusive framework which combines ROM construction with reduced dynamics identification. The proposed approach leverages autoencoder neural networks with parametric sparse identification of nonlinear dynamics (SINDy) to construct a low-dimensional dynamical model. These aim at tracking the evolution of periodic steady-state responses as functions of system parameters, avoiding the computation of the transient phase, and allowing to detect instabilities and bifurcations.
  arXiv  Detail & Related papers  (2022-11-13T01:57:18Z)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• Physics-constrained deep neural network method for estimating parameters in a redox flow battery [68.8204255655161]
  We present a physics-constrained deep neural network (PCDNN) method for parameter estimation in the zero-dimensional (0D) model of the vanadium flow battery (VRFB) We show that the PCDNN method can estimate model parameters for a range of operating conditions and improve the 0D model prediction of voltage. We also demonstrate that the PCDNN approach has an improved generalization ability for estimating parameter values for operating conditions not used in the training.
  arXiv  Detail & Related papers  (2021-06-21T23:42:58Z)
• Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems [0.0]
  A novel multiscale Bayesian inference approach is introduced based on deep probabilistic generative models. The method allows high-dimensional parameter estimation while exhibiting stability, efficiency and accuracy.
  arXiv  Detail & Related papers  (2021-02-04T11:47:21Z)
• Adaptive Physics-Informed Neural Networks for Markov-Chain Monte Carlo [2.741266294612776]
  We focus on a class of parameter estimation problems for which computing the likelihood function requires solving a PDE. The proposed method consists of: (1) constructing an offline PINN-UQ model as an approximation to the forward model; and (2) refining this approximate model on the fly using samples generated from the MCMC sampler. We numerically demonstrate the performance of the proposed APINN method in solving a parameter estimation problem for a system governed by the Poisson equation.
  arXiv  Detail & Related papers  (2020-08-03T15:25:10Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

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.