Wasserstein GAN
read the original abstract
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 corresponding optimization problem is sound, and provide extensive theoretical work highlighting the deep connections to other distances between distributions.
This paper has not been read by Pith yet.
Forward citations
Cited by 38 Pith papers
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
Denoising Diffusion Implicit Models
DDIMs construct non-Markovian diffusion processes that share DDPM training objectives but allow much faster reverse sampling, demonstrated empirically at 10-50x wall-clock speedup.
-
VLTI/PIONIER imaging of post-AGB binaries. An INSPIRING hunt for inner rim substructures in circumbinary discs
High-resolution interferometric imaging of eight post-AGB circumbinary discs reveals diverse inner-rim substructures including azimuthal brightness enhancements and arc-like features not explained by inclination alone.
-
Physics-informed, Generative Adversarial Design of Funicular Shells
A modified DCGAN with an auxiliary discriminator using the membrane factor generates stable, previously unseen funicular shells optimized for pure compression in three dimensions.
-
GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
-
Causal Inference for Spatial Treatments
Develops design-based causal inference methods for spatial treatments using counterfactual candidate locations, extends double ML for spatial correlations, and applies to grocery store effects on foot traffic.
-
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive growing stabilizes GAN training to produce high-resolution images of unprecedented quality and achieves a record unsupervised inception score of 8.80 on CIFAR10.
-
Causal Stability Selection
Causal stability selection identifies treatment effect modifiers with a non-asymptotic bound on expected false positives by integrating cross-fitted CATE estimation and stability selection.
-
Separate Universe Super-Resolution Emulator
A generative adversarial network emulator upscales low-resolution N-body simulations with non-zero curvature to high resolution, recovering most large-scale power but with up to 10% small-scale suppression and altered...
-
On Model-Based Clustering With Entropic Optimal Transport
Entropic optimal transport yields a clustering loss with the same global optimum as log-likelihood but a better-behaved optimization surface, outperforming standard EM in experiments.
-
A unified perspective on fine-tuning and sampling with diffusion and flow models
A unified framework for exponential tilting in diffusion and flow models that includes bias-variance decompositions showing finite gradient variance for some methods, norm bounds on adjoint ODEs, and adapted losses wi...
-
Semantic Segmentation for Histopathology using Learned Regularization based on Global Proportions
VSLP infers dense segmentations from global label proportions via a pre-trained transformer for initial confidence maps followed by variational optimization using Wasserstein fidelity and a learned regularizer, outper...
-
Lookahead Drifting Model
The lookahead drifting model improves upon the drifting model by sequentially computing multiple drifting terms that incorporate higher-order gradient information, leading to better performance on toy examples and CIFAR10.
-
One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization
LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.
-
MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.
-
Dual Adversarial Learning with Attention Mechanism for Fine-grained Medical Image Synthesis
Dual-discriminator GAN with adversarial attention improves fine-grained medical image synthesis, especially in hard-to-generate tumor regions, and outperforms prior methods on brain tumor and CT-to-MRI tasks.
-
Adversarial Computation of Optimal Transport Maps
A GAN with Wasserstein discriminator objective makes the generator follow the W2 geodesic to learn an optimal transport map.
-
Local Bures-Wasserstein Transport: A Practical and Fast Mapping Approximation
A local Gaussian Bures-Wasserstein method approximates transport maps and barycenters, claimed to run 80x faster than kernel baselines while using fewer components.
-
Demystifying MMD GANs
MMD GANs have unbiased critic gradients but biased generator gradients from sample-based learning, and the Kernel Inception Distance provides a practical new measure for GAN convergence and dynamic learning rate adaptation.
-
On the Tradeoffs of On-Device Generative Models in Federated Predictive Maintenance Systems
Experiments on real industrial time series show that partial model sharing improves diffusion model performance in bandwidth-limited non-IID settings, while full sharing stabilizes GAN training but offers less robustn...
-
Finite-Time Analysis of MCTS in Continuous POMDP Planning
The paper proves finite-time probabilistic bounds on value estimates for MCTS in both discrete and continuous POMDPs and introduces Voro-POMCPOW with adaptive partitioning for guarantees.
-
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemph...
-
Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias
Smart Embedding reduces parameters by 48.3 percent in polyphonic music models with information-theoretic loss bounds under 0.153 bits and tighter generalization via Rademacher complexity.
-
State-Conditional Adversarial Learning: An Off-Policy Visual Domain Transfer Method for End-to-End Imitation Learning
SCAL derives an upper bound on target-domain imitation loss using source loss plus state-conditional latent KL divergence and aligns distributions via a discriminator-based adversarial estimator.
-
Generative Inversion for Property-Targeted Materials Design: Application to Shape Memory Alloys
A GAN inversion method coupled with property prediction enables inverse design of NiTi-based SMAs, with experimental validation yielding an alloy at 404°C transformation temperature and 9.9 J/cm³ work output.
-
FMRI data augmentation via synthesis
Empirical evaluation of GMM, GAN, and VAE models for synthesizing diverse task-dependent fMRI images shows they can augment classifiers with performance gains complementary to the choice of predictive model.
-
Justifying Diagnosis Decisions by Deep Neural Networks
A multi-task deep learning model maps frontal X-rays to continuous text for producing diagnoses, textual justifications, and alternative images, with expert study showing better justification than saliency maps.
-
Cellular State Transformations using Generative Adversarial Networks
TSPG applies conditional GANs to generate realistic transcriptome perturbations that mimic source-to-target gene expression state transitions and highlight biologically enriched genes.
-
Adversarial optimization for joint registration and segmentation in prostate CT radiotherapy
An end-to-end 3D adversarial network estimates deformation vector fields to align CT images and propagate segmentations, showing improved performance and speed over elastix for prostate radiotherapy.
-
Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
The study applies an ensemble of machine learning and deep learning models with synthetic oversampling on 2018-2020 data to nowcast visibility, finding a performance decline on 2021 test data attributed to distributio...
-
Conditional Wasserstein GAN for Simulating Neutrino Event Summaries using Incident Energy of Electron Neutrinos
A conditional Wasserstein GAN generates complete kinematic event summaries for IBD-CC, NC, and NuEElastic electron neutrino interactions that match GENIE distributions in 1D marginals and correlations.
-
Hierarchical Sequence to Sequence Voice Conversion with Limited Data
Hierarchical seq2seq model for parallel voice conversion pretrained as autoencoder on single-speaker data then adapted to limited multispeaker data, using mel spectrograms converted via wavenet vocoder.
-
Mean Spectral Normalization of Deep Neural Networks for Embedded Automation
Proposes MSN reparameterization to address mean-drift in SN, claiming ~16% faster inference than BN with fewer parameters on CNNs and GANs.
-
Incremental Concept Learning via Online Generative Memory Recall
Pseudo-rehearsal method with cGAN-generated old-concept samples, balanced online recall, and concept contrastive loss for class-incremental learning on MNIST, Fashion-MNIST and SVHN.
-
MIDI-Sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN networks for Symbolic Single-track Music Generation
MIDI-Sandwich is a hierarchical VAE-GAN architecture that generates structured 136-beat melodies by modeling local bars and global relationships on the Nottingham dataset.
-
Physics-driven Comparative Analysis of Various Statistical Distance Metrics and Normalizing Functions
A data-driven comparison of Hellinger, Wasserstein, Jensen-Shannon, Kolmogorov-Smirnov and other distance metrics on Kr-83 decay spectra finds varying stability of a chosen parameter of interest depending on sample si...
-
Improving Detection of Credit Card Fraudulent Transactions using Generative Adversarial Networks
Wasserstein GAN generates synthetic fraud transactions that improve classifier performance on credit card data more stably than standard or conditional GAN variants.
-
Implementation of batched Sinkhorn iterations for entropy-regularized Wasserstein loss
Documents a practical PyTorch implementation of batched Sinkhorn iterations for the entropy-regularized Wasserstein loss introduced by Cuturi.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.