A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Filters
Wasserstein discriminant analysis
2018
Machine Learning
Preserved Fulltext
Other Versions
Wasserstein Discriminant Analysis (WDA) is a new supervised method that can improve classification of high-dimensional data by computing a suitable linear map onto a lower dimensional subspace. ...
Following the blueprint of classical Linear Discriminant Analysis (LDA), WDA selects the projection matrix that maximizes the ratio of two quantities: the dispersion of projected points coming from different ...
Conclusion This work presents the Wasserstein Discriminant Analysis, a new and original linear discriminant subspace estimation method. ...
doi:10.1007/s10994-018-5717-1
fatcat:lku64gfoljfm3g2voxiopgicpu
Ratio Trace Formulation of Wasserstein Discriminant Analysis
2020
Neural Information Processing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
We reformulate the Wasserstein Discriminant Analysis (WDA) as a ratio trace problem and present an eigensolver-based algorithm to compute the discriminative subspace of WDA. ...
We provide a rigorous convergence analysis for the proposed algorithm under the self-consistent field framework, which is crucial but missing in the literature. ...
Introduction Wasserstein Discriminant Analysis (WDA) [13] is a supervised linear dimensionality reduction technique that generalizes the classical Fisher Discriminant Analysis (FDA) [16] using the ...
dblp:conf/nips/LiuCCL20
fatcat:33arjsyegbcjlblsvfk4wpnjha
Max-Sliced Wasserstein Distance and its use for GANs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We first show that the recently proposed sliced Wasserstein distance has compelling sample complexity properties when compared to the Wasserstein distance. ...
To further improve the sliced Wasserstein distance we then analyze its 'projection complexity' and develop the max-sliced Wasserstein distance which enjoys compelling sample complexity while reducing projection ...
and Max-Sliced Distance In this section we provide the first analysis of the samplecomplexity benefits of the sliced Wasserstein distance compared to the Wasserstein distance. ...
arXiv:1904.05877v1
fatcat:xvvod74kzbetjgygzgxgi4c6de
Max-Sliced Wasserstein Distance and Its Use for GANs
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We first show that the recently proposed sliced Wasserstein distance has compelling sample complexity properties when compared to the Wasserstein distance. ...
To further improve the sliced Wasserstein distance we then analyze its 'projection complexity' and develop the max-sliced Wasserstein distance which enjoys compelling sample complexity while reducing projection ...
and Max-Sliced Distance In this section we provide the first analysis of the samplecomplexity benefits of the sliced Wasserstein distance compared to the Wasserstein distance. ...
doi:10.1109/cvpr.2019.01090
dblp:conf/cvpr/DeshpandeHSPSKZ19
fatcat:5pq3ivkskbacxej4zggbgitw4u
Orthogonal Wasserstein GANs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
However, Wasserstein-GANs require the discriminator to be Lipschitz continuous. In current state-of-the-art Wasserstein-GANs this constraint is enforced via gradient norm regularization. ...
Finally, we provide a novel metric to evaluate the generalization capabilities of the discriminators of different Wasserstein-GANs. ...
Analysis of mode preservation for different WGAN approaches One of the main benefits of Wasserstein GANs over standard GANs is their capability to mitigate mode collapse. ...
arXiv:1911.13060v2
fatcat:pa4ay575wrgkfgytypw5uztgiy
Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We provide an in-depth mathematical analysis of differences between the theoretical setup and the reality of training Wasserstein GANs. ...
Wasserstein GANs are based on the idea of minimising the Wasserstein distance between a real and a generated distribution. ...
Choosing the right divergence A rigorous mathematical analysis of the vanilla GAN's optimal discriminator dynamics has been performed in . ...
arXiv:2103.01678v4
fatcat:lzbp2t545jabzk2ategxvr6qhu
Wasserstein Distance Learns Domain Invariant Feature Representations for Drift Compensation of E-Nose
2019
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
It regards a neural network as a domain discriminator to measure the empirical Wasserstein distance between the source domain (data without drift) and target domain (drift data). ...
The WDLFR minimizes Wasserstein distance by optimizing the feature extractor in an adversarial manner. The Wasserstein distance for domain adaption has good gradient and generalization bound. ...
In order to better verify the effectiveness of the proposed WDLFR method in this paper, the proposed approach compares with principal component analysis (PCA) [8] , linear discriminant analysis (LDA) ...
doi:10.3390/s19173703
fatcat:nispyyu3d5ebxhhbwblzcr3ziq
Linear Discriminant Generative Adversarial Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). ...
between generators and discriminators in the unsupervised case, without employment of normalization methods and constraints on weights. ...
Linear Discriminant Analysis Linear Discriminant Analysis (LDA) methods are used to compute a linear combination of features which characterize or separate two or more classes of objects. ...
arXiv:1707.07831v1
fatcat:ffoziw4hhvgjnjdrh4itagrioi
Wasserstein Distance Guided Representation Learning for Domain Adaptation
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
estimated Wasserstein distance in an adversarial manner. ...
One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. ...
Theoretical Analysis In this section, we give some theoretical analysis about the advantages of using Wasserstein distance for domain adaptation. ...
arXiv:1707.01217v4
fatcat:znq72ztuufa3fc4pgymmor23bm
Generative Modeling Using the Sliced Wasserstein Distance
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. ...
While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein ...
In theory this can be addressed by methods such as linear discriminant analysis, but they are expensive. ...
doi:10.1109/cvpr.2018.00367
dblp:conf/cvpr/DeshpandeZS18
fatcat:2ewcg6v7mncmhotqykcih5jqbu
Wasserstein Distance guided Adversarial Imitation Learning with Reward Shape Exploration
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we propose a new algorithm named Wasserstein Distance guided Adversarial Imitation Learning (WDAIL) for promoting the performance of imitation learning (IL). ...
There are three improvements in our method: (a) introducing the Wasserstein distance to obtain more appropriate measure in adversarial training process, (b) using proximal policy optimization (PPO) in ...
The L 1 -Wasserstein distance is more flexible and easier to bound and it has strong implications in functional analysis. ...
arXiv:2006.03503v1
fatcat:i5atdc456vfeheaxqijf2kys7i
Generative Modeling using the Sliced Wasserstein Distance
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. ...
While this is particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein ...
For faster convergence it is, therefore, better to use projections along which the distributions are In theory this can be addressed by methods such as linear discriminant analysis, but they are expensive ...
arXiv:1803.11188v1
fatcat:w24rmcq3wbbhpa5o23trx2z7ae
Towards Efficient and Unbiased Implementation of Lipschitz Continuity in GANs
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
It was observed that the Lipschitz regularized discriminator leads to improved training stability and sample quality. ...
Our experiments verify our analysis and show that the proposed method is able to achieve successful training in various situations where gradient penalty and spectral normalization fail. ...
Unfortunately, regularized Wasserstein distance usually also alters the property of the optimal discriminative function and blurs the π * [Seguy et al., 2017], which is consistent with our analysis here ...
arXiv:1904.01184v1
fatcat:6e3beuwxpnfq3doqgergpn5nue
Wasserstein Adversarially Regularized Graph Autoencoder
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
via the Wasserstein metric. ...
This paper introduces Wasserstein Adversarially Regularized Graph Autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution ...
For instance, Wasserstein Generative Adversarial Networks (WGAN) [2] replaces the discriminator in Generative Adversarial Nets (GAN) [4] by Wasserstein metric to handle the problems of unstable training ...
arXiv:2111.04981v1
fatcat:afco4smx6ffmdic4cjypkjhnry
WRGAN: Improvement of RelGAN with Wasserstein Loss for Text Generation
2021
Electronics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Differently from RelGAN, we modified the discriminator network structure with 1D convolution of multiple different kernel sizes. ...
Compared with the current loss function, the Wasserstein distance can provide more information to the generator, but RelGAN does not work well with Wasserstein distance in experiments. ...
WGAN converts the discriminator from a binary classification task into an approximately fitting Wasserstein distance. ...
doi:10.3390/electronics10030275
fatcat:d6amgpspkrhyxdmqlh6x5ygczi
« Previous
Showing results 1 — 15 out of 5,861 results