A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper optimizes WGAN parameters for non-Gaussian data.
PT-WGAN reduces PET image noise without losing details.
This study improves numeric data generation using constrained WGAN structures.
DAG-WGAN learns causal structures using Wasserstein distance.
Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution. Recent studies have proposed stabilizing the training process for the WGAN and implementing the Lipschitz constraint. In this study, we prove the local stability of optimizing the simple gradien…
Wasserstein Generative Adversarial Networks (WGANs) provide a versatile class of models, which have attracted great attention in various applications. However, this framework has two main drawbacks: (i) Wasserstein-1 (or Earth-Mover) distance is restrictive such that WGANs cannot always fit data geometry well; (ii) It …
WGANs use optimal 1-Wasserstein distance to generate distributions.
Paper bridges -GANs and WGANs for better image generation.
SGD finds global optima in WGANs for 1-layer generators.
The paper explores theoretical insights into WGANs for better understanding and stability.
Wasserstein GANs with Gradient Penalty compute a different optimal transport problem called congested transport.
Generative adversarial network improves audio inpainting for long gaps.
WGAN-GP generates Bitcoin-like financial time series.
The paper introduces a new ODE approach to improve Wasserstein GANs.
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only low-quality samples or fail to converge. We find that these problems are often du…
Generative Adversial Networks (GANs) have made a major impact in computer vision and machine learning as generative models. Wasserstein GANs (WGANs) brought Optimal Transport (OT) theory into GANs, by minimizing the -Wasserstein distance between model and data distributions as their objective function. Since then, W…
The study provides statistical theory for WGANs in time series forecasting.
Paper relaxes the Lipschitz constraint in WGANs to improve performance.
We know SGAN may have a risk of gradient vanishing. A significant improvement is WGAN, with the help of 1-Lipschitz constraint on discriminator to prevent from gradient vanishing. Is there any GAN having no gradient vanishing and no 1-Lipschitz constraint on discriminator? We do find one, called GAN-QP. To construct a …
We address the issue of limit cycling behavior in training Generative Adversarial Networks and propose the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs. Recent theoretical results have shown that optimistic mirror decent (OMD) can enjoy faster regret rates in the context of zero-sum games. WGANs …
WGANs improve probability distribution approximation with depth and width trade-offs.
Generative modeling over natural images is one of the most fundamental machine learning problems. However, few modern generative models, including Wasserstein Generative Adversarial Nets (WGANs), are studied on manifold-valued images that are frequently encountered in real-world applications. To fill the gap, this pape…
GS-WGAN sanitizes sensitive data for machine learning with improved privacy and model quality.
Despite being impactful on a variety of problems and applications, the generative adversarial nets (GANs) are remarkably difficult to train. This issue is formally analyzed by \cite{arjovsky2017towards}, who also propose an alternative direction to avoid the caveats in the minmax two-player training of GANs. The corres…
Optimized GAN discriminator using polyharmonic interpolation.
Generative Adversarial Networks (GANs) have been promising in the field of image generation, however, they have been hard to train for language generation. GANs were originally designed to output differentiable values, so discrete language generation is challenging for them which causes high levels of instability in tr…
GANs struggle with density estimation on simple datasets, while normalizing flows perform well.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
The paper trains neural networks with robustness guarantees using semidefinite constraints.
Wasserstein distance improves GANs by reducing training difficulties.
This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to improve GANs' training by adopting a smooth metric for measuring the distance between two probability distributions.
New findings on optimal transport gradient for generative models, addressing numerical instabilities.
Unsupervised learning with generative adversarial networks (GANs) has proven to be hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process…
Generative model creates EEG data for RSVP experiments.
We introduce a new algorithm named WGAN, an alternative to traditional GAN training. In this new model, we show that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches. Furthermore, we show that the co…
Proposes GM Score to evaluate GANs considering diversity, disentanglement, and discriminability.
FE-GAN improves VaR and ES estimation in financial risk management.
In this paper, we study the convergence of generative adversarial networks (GANs) from the perspective of the informativeness of the gradient of the optimal discriminative function. We show that GANs without restriction on the discriminative function space commonly suffer from the problem that the gradient produced by …
Study robust distribution estimation with Wasserstein distance, achieving optimal risk.
Generative adversarial networks create synthetic insurance datasets from confidential originals.
iWGAN improves GANs by stabilizing training and preventing mode collapse.
Proposes Sig-Wasserstein GANs for generating time series with temporal dependence.
New approach stabilizes GANs by leveraging implicit competitive regularization.
Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a nat…
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to voco…
POTNet uses penalized optimal transport to generate data without mode collapse.
We developed a new class of physics-informed generative adversarial networks (PI-GANs) to solve in a unified manner forward, inverse and mixed stochastic problems based on a limited number of scattered measurements. Unlike standard GANs relying only on data for training, here we encoded into the architecture of GANs th…
We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs. The MH-GAN draws samples from the distribution implicitly defined by a GAN's discriminator-generator pair, as opposed to standard GANs which draw samples from the distribution defin…