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.
Wasserstein GANs fail to approximate Wasserstein distance, leading to their success.
Vanilla GANs are connected to Wasserstein distance for better understanding.
Generative adversarial networks (GANs) have enjoyed much success in learning high-dimensional distributions. Learning objectives approximately minimize an -divergence (-GANs) or an integral probability metric (Wasserstein GANs) between the model and the data distribution using a discriminator. Wasserstein GANs en…
Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train. Recently, a series of papers (Arjovsky & Bottou, 2017a; Arjovsky et al. 2017b; and Gu…
Improved GAN performance using higher-order Wasserstein moments.
Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved convergence behaviour and improved image quality. However, Wasserstein-GANs require the discriminator to be…
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 improves PAC-Bayesian bounds for adversarial generative models.
Paper proposes robust estimators for GANs under Wasserstein contamination.
Paper relaxes the Lipschitz constraint in WGANs to improve performance.
We investigate the training and performance of generative adversarial networks using the Maximum Mean Discrepancy (MMD) as critic, termed MMD GANs. As our main theoretical contribution, we clarify the situation with bias in GAN loss functions raised by recent work: we show that gradient estimators used in the optimizat…
The paper explores multidimensional critic output in GANs, improving convergence and diversity.
Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to model high-dimensional distributions, sequential training and stacked architectures …
Wasserstein GANs are shown to have hidden convexity, enabling exact solutions with convex optimization.
iWGAN improves GANs by stabilizing training and preventing mode collapse.
MonoFlow rethinks GANs using Wasserstein gradient flows.
Generative Adversarial Networks (GANs) have been used to model the underlying probability distribution of sample based datasets. GANs are notoriuos for training difficulties and their dependence on arbitrary hyperparameters. One recent improvement in GAN literature is to use the Wasserstein distance as loss function le…
Generative adversarial networks are a class of generative algorithms that have been widely used to produce state-of-the-art samples. In this paper, we investigate GAN to perform anomaly detection on time series dataset. In order to achieve this goal, a bibliography is made focusing on theoretical properties of GAN and …
Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to b…
GANICE improves GAN-based causal inference by minimizing averaged Wasserstein risk.
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.
Simplified GAN model shows how discriminator improves generalization.
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
The paper introduces a new ODE approach to improve Wasserstein GANs.
The paper introduces a new Wasserstein distance for approximating posteriors in inverse problems.
Paper optimizes WGAN parameters for non-Gaussian data.
Generative Adversarial Networks (GANs) have become a powerful framework to learn generative models that arise across a wide variety of domains. While there has been a recent surge in the development of numerous GAN architectures with distinct optimization metrics, we are still lacking in our understanding on how far aw…
New findings suggest minimax optimality doesn't guarantee distribution learning for GANs.
This report has several purposes. First, our report is written to investigate the reproducibility of the submitted paper On the regularization of Wasserstein GANs (2018). Second, among the experiments performed in the submitted paper, five aspects were emphasized and reproduced: learning speed, stability, robustness ag…
New method simulates multivariate extreme events using GANs and Aitchison coordinates.
Generative adversarial networks (GANs) are an exciting alternative to algorithms for solving density estimation problems---using data to assess how likely samples are to be drawn from the same distribution. Instead of explicitly computing these probabilities, GANs learn a generator that can match the given probabilisti…
A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated.…
Generative Adversarial Networks (GANs) are one of the most practical methods for learning data distributions. A popular GAN formulation is based on the use of Wasserstein distance as a metric between probability distributions. Unfortunately, minimizing the Wasserstein distance between the data distribution and the gene…
While Generative Adversarial Networks (GANs) have empirically produced impressive results on learning complex real-world distributions, recent works have shown that they suffer from lack of diversity or mode collapse. The theoretical work of Arora et al. suggests a dilemma about GANs' statistical properties: powerful d…
In this paper, we investigate the underlying factor that leads to failure and success in the training of GANs. We study the property of the optimal discriminative function and show that in many GANs, the gradient from the optimal discriminative function is not reliable, which turns out to be the fundamental cause of fa…
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…
Wasserstein GANs with Gradient Penalty compute a different optimal transport problem called congested transport.
Study extends DRO with IPMs, linking robustness to regularization and GANs.
A new GAN loss function based on cumulant generating functions improves stability and robustness.
Estimates intrinsic dimension of data for GANs.
The paper explores theoretical insights into WGANs for better understanding and stability.
Adaptive framework for learning latent space dimensions in GANs.
This study analyzes how well GANs approximate distributions from small samples.
Proposes Sig-Wasserstein GANs for generating time series with temporal dependence.
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 …
Generates realistic stock market order streams using GANs.
Optimized GAN discriminator using polyharmonic interpolation.
The paper studies how different entropic regularizations affect GAN solutions.