A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks

• URL: http://arxiv.org/abs/2404.07172v1
• Date: Wed, 10 Apr 2024 17:08:46 GMT
• Title: A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networks
• Authors: Neel Mishra, Bamdev Mishra, Pratik Jawanpuria, Pawan Kumar,
• Abstract summary: A novel first-order method is proposed for training generative adversarial networks (GANs) It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets.
• Score: 7.217857709620766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method corresponds to a fixed-point method that ensures necessary contraction. To evaluate its effectiveness, numerical experiments are conducted on various datasets commonly used in image generation tasks, such as MNIST, Fashion MNIST, CIFAR10, FFHQ, and LSUN. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets. It also achieves the highest inception score for CIFAR10 among all compared methods, including state-of-the-art second-order methods. Additionally, its execution time is comparable to that of first-order min-max methods.

Related papers

• Ensemble Quadratic Assignment Network for Graph Matching [52.20001802006391]
  Graph matching is a commonly used technique in computer vision and pattern recognition. Recent data-driven approaches have improved the graph matching accuracy remarkably. We propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
  arXiv  Detail & Related papers  (2024-03-11T06:34:05Z)
• Inverse-Free Fast Natural Gradient Descent Method for Deep Learning [52.0693420699086]
  We present a fast natural gradient descent (FNGD) method that only requires inversion during the first epoch. FNGD exhibits similarities to the average sum in first-order methods, leading to the computational complexity of FNGD being comparable to that of first-order methods.
  arXiv  Detail & Related papers  (2024-03-06T05:13:28Z)
• Adaptive Consensus Optimization Method for GANs [2.1227526213206542]
  We propose a second order gradient based method with ADAM and RMSprop for the training of generative adversarial networks. We derive the fixed point iteration corresponding to proposed method, and show that the proposed method is convergent. The proposed method produces better or comparable inception scores, and comparable quality of images compared to other recently proposed state-of-the-art second order methods.
  arXiv  Detail & Related papers  (2023-04-20T13:50:42Z)
• Nystrom Method for Accurate and Scalable Implicit Differentiation [25.29277451838466]
  We show that the Nystrom method consistently achieves comparable or even superior performance to other approaches. The proposed method avoids numerical instability and can be efficiently computed in matrix operations without iterations.
  arXiv  Detail & Related papers  (2023-02-20T02:37:26Z)
• A Stochastic Bundle Method for Interpolating Networks [18.313879914379008]
  We propose a novel method for training deep neural networks that are capable of driving the empirical loss to zero. At each iteration our method constructs a maximum linear approximation, known as the bundle of the objective learning approximation.
  arXiv  Detail & Related papers  (2022-01-29T23:02:30Z)
• Fast Differentiable Matrix Square Root and Inverse Square Root [65.67315418971688]
  We propose two more efficient variants to compute the differentiable matrix square root and the inverse square root. For the forward propagation, one method is to use Matrix Taylor Polynomial (MTP), and the other method is to use Matrix Pad'e Approximants (MPA) A series of numerical tests show that both methods yield considerable speed-up compared with the SVD or the NS iteration.
  arXiv  Detail & Related papers  (2022-01-29T10:00:35Z)
• Comparison of Methods Generalizing Max- and Average-Pooling [1.693200946453174]
  Max- and average-pooling are the most popular methods for downsampling in convolutional neural networks. In this paper, we compare different pooling methods that generalize both max- and average-pooling. The results show that none of the more sophisticated methods perform significantly better in this classification task than standard max- or average-pooling.
  arXiv  Detail & Related papers  (2021-03-02T14:26:51Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)
• Optimal Randomized First-Order Methods for Least-Squares Problems [56.05635751529922]
  This class of algorithms encompasses several randomized methods among the fastest solvers for least-squares problems. We focus on two classical embeddings, namely, Gaussian projections and subsampled Hadamard transforms. Our resulting algorithm yields the best complexity known for solving least-squares problems with no condition number dependence.
  arXiv  Detail & Related papers  (2020-02-21T17:45:32Z)
• Gaussian Mixture Reduction with Composite Transportation Divergence [15.687740538194413]
  We propose a novel optimization-based GMR method based on composite transportation divergence (CTD) We develop a majorization-minimization algorithm for computing the reduced mixture and establish its theoretical convergence. Our unified framework empowers users to select the most appropriate cost function in CTD to achieve superior performance.
  arXiv  Detail & Related papers  (2020-02-19T19:52:17Z)
• Clustering Binary Data by Application of Combinatorial Optimization Heuristics [52.77024349608834]
  We study clustering methods for binary data, first defining aggregation criteria that measure the compactness of clusters. Five new and original methods are introduced, using neighborhoods and population behavior optimization metaheuristics. From a set of 16 data tables generated by a quasi-Monte Carlo experiment, a comparison is performed for one of the aggregations using L1 dissimilarity, with hierarchical clustering, and a version of k-means: partitioning around medoids or PAM.
  arXiv  Detail & Related papers  (2020-01-06T23:33:31Z)

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.