StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations

• URL: http://arxiv.org/abs/2101.00574v1
• Date: Sun, 3 Jan 2021 08:06:42 GMT
• Title: StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
• Authors: Amir Zadeh, Santiago Benoit, Louis-Philippe Morency
• Abstract summary: We present an approach for training deep generative models based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable properties.
• Score: 47.72653430712088
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper we present an approach for training deep generative models solely based on solving determined systems of linear equations. A network that uses this approach, called a StarNet, has the following desirable properties: 1) training requires no gradient as solution to the system of linear equations is not stochastic, 2) is highly scalable when solving the system of linear equations w.r.t the latent codes, and similarly for the parameters of the model, and 3) it gives desirable least-square bounds for the estimation of latent codes and network parameters within each layer.

Related papers

• Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers [42.69799418639716]
  Deep learning models may be used to precondition residuals during iteration of such linear solvers as the conjugate gradient (CG) method. Neural network models require an enormous number of parameters to approximate well in this setup. In our work, we recall well-established preconditioners from linear algebra and use them as a starting point for training the GNN.
  arXiv  Detail & Related papers  (2024-05-24T13:44:30Z)
• An L-BFGS-B approach for linear and nonlinear system identification under $\ell_1$- and group-Lasso regularization [0.0]
  We propose a very efficient numerical method for identifying linear and nonlinear discrete-time state-space models. A Python implementation of the proposed identification method is available in the package jax-sysid.
  arXiv  Detail & Related papers  (2024-03-06T16:17:34Z)
• Generalized Quadratic Embeddings for Nonlinear Dynamics using Deep Learning [11.339982217541822]
  We present a data-driven methodology for modeling the dynamics of nonlinear systems. In this work, we propose using quadratic systems as the common structure, inspired by the lifting principle.
  arXiv  Detail & Related papers  (2022-11-01T10:03:34Z)
• Message Passing Neural PDE Solvers [60.77761603258397]
  We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
  arXiv  Detail & Related papers  (2022-02-07T17:47:46Z)
• Unsupervised Reservoir Computing for Solving Ordinary Differential Equations [1.6371837018687636]
  unsupervised reservoir computing (RC), an echo-state recurrent neural network capable of discovering approximate solutions that satisfy ordinary differential equations (ODEs) We use Bayesian optimization to efficiently discover optimal sets in a high-dimensional hyper- parameter space and numerically show that one set is robust and can be used to solve an ODE for different initial conditions and time ranges.
  arXiv  Detail & Related papers  (2021-08-25T18:16:42Z)
• Linear embedding of nonlinear dynamical systems and prospects for efficient quantum algorithms [74.17312533172291]
  We describe a method for mapping any finite nonlinear dynamical system to an infinite linear dynamical system (embedding) We then explore an approach for approximating the resulting infinite linear system with finite linear systems (truncation)
  arXiv  Detail & Related papers  (2020-12-12T00:01:10Z)
• Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation [16.64525769134209]
  We explore the performance and accuracy of various neural architectures on both linear and nonlinear differential equations. We implement a novel Legendre-Galerkin Deep Neural Network (LGNet) algorithm to predict solutions to differential equations.
  arXiv  Detail & Related papers  (2020-10-24T20:25:09Z)
• 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)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)
• Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems [107.3868459697569]
  We introduce an eigendecomposition-free approach to training a deep network. We show that our approach is much more robust than explicit differentiation of the eigendecomposition. Our method has better convergence properties and yields state-of-the-art results.
  arXiv  Detail & Related papers  (2020-04-15T04:29:34Z)

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.