paper-with-me

Papers

Conjugate Gradient Method for Generative Adversarial Networks

2022-03-28 · Hiroki Naganuma, Hideaki Iiduka

One of the training strategies of generative models is to minimize the Jensen--Shannon divergence between the model distribution and the data distribution. Since data distribution is unknown, generative adversarial networks (GANs) formulate this problem as a game between two models, a generator and a discriminator. The training can be formulated in the context of game theory and the local Nash equilibrium (LNE). It does not seem feasible to derive guarantees of stability or optimality for the existing methods. This optimization problem is far more challenging than the single objective setting. Here, we use the conjugate gradient method to reliably and efficiently solve the LNE problem in GANs. We give a proof and convergence analysis under mild assumptions showing that the proposed method converges to a LNE with three different learning rate update rules, including a constant learning rate. Finally, we demonstrate that the proposed method outperforms stochastic gradient descent (SGD) and momentum SGD in terms of best Frechet inception distance (FID) score and outperforms Adam on average. The code is available at \url{https://github.com/Hiroki11x/ConjugateGradient_GAN}.

📄 PDF Abstract BibTeX arXiv:2203.14495

Code (1)

hiroki11x/conjugategradient_gan 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Adam 설명 없음
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Scaled Conjugate Gradient Method for Nonconvex Optimization in Deep Neural Networks

2024-12-16 · Naoki Sato, Koshiro Izumi, Hideaki Iiduka

A scaled conjugate gradient method that accelerates existing adaptive methods utilizing stochastic gradients is proposed for solving nonconvex optimization problems with deep neural networks. It is shown theoretically th…

text-classificationText Classification

Diversified Adversarial Attacks based on Conjugate Gradient Method

2022-06-20 · Keiichiro Yamamura, Haruki Sato, Nariaki Tateiwa, Nozomi Hata 외

Deep learning models are vulnerable to adversarial examples, and adversarial attacks used to generate such examples have attracted considerable research interest. Although existing methods based on the steepest descent h…

Diversity

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks

2024-08-07 · Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa

Deep neural networks are vulnerable to adversarial examples, and adversarial attacks that generate adversarial examples have been studied in this context. Existing studies imply that increasing the diversity of model out…

Diversity

Stochastic Gradient Descent with Nonlinear Conjugate Gradient-Style Adaptive Momentum

2020-12-03 · Bao Wang, Qiang Ye

Momentum plays a crucial role in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well…

Adversarial Robustness

Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models

2017-03-13 · Mohammad Emtiyaz Khan, Wu Lin

Variational inference is computationally challenging in models that contain both conjugate and non-conjugate terms. Methods specifically designed for conjugate models, even though computationally efficient, find it diffi…

Variational Inference