Generative Adversarial Method Based on Neural Tangent Kernels

• URL: http://arxiv.org/abs/2204.04090v2
• Date: Mon, 11 Apr 2022 06:03:06 GMT
• Title: Generative Adversarial Method Based on Neural Tangent Kernels
• Authors: Yu-Rong Zhang, Sheng Yen Chou, Shan-Hung Wu
• Abstract summary: We propose a new generative algorithm called generative adversarial NTK (GA-NTK) GA-NTK can generate images comparable to those by GANs but is much easier to train under various conditions. We conduct extensive experiments on real-world datasets, and the results show that GA-NTK can generate images comparable to those by GANs but is much easier to train under various conditions.
• Score: 13.664682865991255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent development of Generative adversarial networks (GANs) has driven many computer vision applications. Despite the great synthesis quality, training GANs often confronts several issues, including non-convergence, mode collapse, and gradient vanishing. There exist several workarounds, for example, regularizing Lipschitz continuity and adopting Wasserstein distance. Although these methods can partially solve the problems, we argue that the problems are result from modeling the discriminator with deep neural networks. In this paper, we base on newly derived deep neural network theories called Neural Tangent Kernel (NTK) and propose a new generative algorithm called generative adversarial NTK (GA-NTK). The GA-NTK models the discriminator as a Gaussian Process (GP). With the help of the NTK theories, the training dynamics of GA-NTK can be described with a closed-form formula. To synthesize data with the closed-form formula, the objectives can be simplified into a single-level adversarial optimization problem. We conduct extensive experiments on real-world datasets, and the results show that GA-NTK can generate images comparable to those by GANs but is much easier to train under various conditions. We also study the current limitations of GA-NTK and propose some workarounds to make GA-NTK more practical.

Related papers

• First-order PDES for Graph Neural Networks: Advection And Burgers Equation Models [1.4174475093445238]
  This paper presents new Graph Neural Network models that incorporate two first-order Partial Differential Equations (PDEs) Our experimental findings highlight the capacity of our new PDE model to achieve comparable results with higher-order PDE models and fix the over-smoothing problem up to 64 layers. Results underscore the adaptability and versatility of GNNs, indicating that unconventional approaches can yield outcomes on par with established techniques.
  arXiv  Detail & Related papers  (2024-04-03T21:47:02Z)
• A practical existence theorem for reduced order models based on convolutional autoencoders [0.4604003661048266]
  Deep learning has gained increasing popularity in the fields of Partial Differential Equations (PDEs) and Reduced Order Modeling (ROM) CNN-based autoencoders have proven extremely effective, outperforming established techniques, such as the reduced basis method, when dealing with complex nonlinear problems. We provide a new practical existence theorem for CNN-based autoencoders when the parameter-to-solution map is holomorphic.
  arXiv  Detail & Related papers  (2024-02-01T09:01:58Z)
• Efficient kernel surrogates for neural network-based regression [0.8030359871216615]
  We study the performance of the Conjugate Kernel (CK), an efficient approximation to the Neural Tangent Kernel (NTK) We show that the CK performance is only marginally worse than that of the NTK and, in certain cases, is shown to be superior. In addition to providing a theoretical grounding for using CKs instead of NTKs, our framework suggests a recipe for improving DNN accuracy inexpensively.
  arXiv  Detail & Related papers  (2023-10-28T06:41:47Z)
• From NeurODEs to AutoencODEs: a mean-field control framework for width-varying Neural Networks [68.8204255655161]
  We propose a new type of continuous-time control system, called AutoencODE, based on a controlled field that drives dynamics. We show that many architectures can be recovered in regions where the loss function is locally convex.
  arXiv  Detail & Related papers  (2023-07-05T13:26:17Z)
• Inference of Regulatory Networks Through Temporally Sparse Data [5.495223636885796]
  A major goal in genomics is to properly capture the complex dynamical behaviors of gene regulatory networks (GRNs) This paper develops a scalable and efficient topology inference for GRNs using Bayesian optimization and kernel-based methods.
  arXiv  Detail & Related papers  (2022-07-21T22:48:12Z)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• A Biased Graph Neural Network Sampler with Near-Optimal Regret [57.70126763759996]
  Graph neural networks (GNN) have emerged as a vehicle for applying deep network architectures to graph and relational data. In this paper, we build upon existing work and treat GNN neighbor sampling as a multi-armed bandit problem. We introduce a newly-designed reward function that introduces some degree of bias designed to reduce variance and avoid unstable, possibly-unbounded payouts.
  arXiv  Detail & Related papers  (2021-03-01T15:55:58Z)
• A Unified View on Graph Neural Networks as Graph Signal Denoising [49.980783124401555]
  Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models can be regarded as solving a graph denoising problem. We instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes.
  arXiv  Detail & Related papers  (2020-10-05T04:57:18Z)
• 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)
• Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks [60.22494363676747]
  It is known that the current graph neural networks (GNNs) are difficult to make themselves deep due to the problem known as over-smoothing. Multi-scale GNNs are a promising approach for mitigating the over-smoothing problem. We derive the optimization and generalization guarantees of transductive learning algorithms that include multi-scale GNNs.
  arXiv  Detail & Related papers  (2020-06-15T17:06:17Z)

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.