Pith. sign in

REVIEW 22 cited by

Wasserstein Auto-Encoders

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1711.01558 v4 pith:JY7Z7SZ2 submitted 2017-11-05 stat.ML cs.LG

classification stat.MLcs.LG
keywords distributionwassersteinalgorithmauto-encoderauto-encodersmodelregularizertraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for building a generative model of the data distribution. WAE minimizes a penalized form of the Wasserstein distance between the model distribution and the target distribution, which leads to a different regularizer than the one used by the Variational Auto-Encoder (VAE). This regularizer encourages the encoded training distribution to match the prior. We compare our algorithm with several other techniques and show that it is a generalization of adversarial auto-encoders (AAE). Our experiments show that WAE shares many of the properties of VAEs (stable training, encoder-decoder architecture, nice latent manifold structure) while generating samples of better quality, as measured by the FID score.

Discussion (0). Sign in to comment.

Forward citations

Cited by 22 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    The paper identifies distinct failure mechanisms: excessive posterior-prior regularization erases mode information in latent policies, while smooth base-to-action maps limit mode coverage in generative policies.

  2. One-Step Generative Modeling via Wasserstein Gradient Flows

    cs.LG 2026-05 conditional novelty 7.0 of 10

    W-Flow achieves state-of-the-art one-step ImageNet 256x256 generation at 1.29 FID by training a static neural network to follow a Wasserstein gradient flow that minimizes Sinkhorn divergence, delivering roughly 100x f...

  3. Optimal Stability of KL Divergence under Gaussian Perturbations

    cs.LG 2026-04 unverdicted novelty 7.0 of 10

    KL divergence between a general distribution and a perturbed Gaussian reference remains stable with an optimal sqrt(ε) degradation rate under finite second-moment conditions.

  4. $\mathbf{\lambda}$-VAE: Variance Equalization for Posterior Collapse

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Scaling VAE reparameterization noise by a per-dimension exponent while keeping KL on the original variance equalizes latent variances and reduces posterior collapse.

  5. Continuous Reasoning for Vision-Language-Action

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    Continuous Reasoning for VLA introduces a shared Gaussian latent for continuous thoughts, trained with self-verification to improve action prediction on LIBERO-PRO and real robots.

  6. Mechanisms of Misgeneralization in Physical Sequence Modeling

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance o...

  7. ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    ArcVQ-VAE constrains VQ-VAE codebook vectors inside a time-dependent ball and adds angular margin loss to increase separability and codebook utilization.

  8. One-Step Generative Modeling via Wasserstein Gradient Flows

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    W-Flow compresses a Wasserstein gradient flow defined via Sinkhorn divergence into a single-step neural generator, reporting 1.29 FID on ImageNet 256x256 with improved mode coverage.

  9. Nonlinear Stochastic Model Predictive Control with Generative Uncertainty in Homogeneous Charge Compression Ignition

    eess.SY 2026-04 unverdicted novelty 6.0 of 10

    A stochastic MPC controller for HCCI engines using learned uncertainty distributions, polynomial chaos expansion, and an MMD-based cost reduces combustion phasing variation by over 28% and improves load tracking by ov...

  10. Well-Posed KL-Regularized Control via Wasserstein and Kalman-Wasserstein KL Divergences

    math.OC 2026-02 conditional novelty 6.0 of 10

    Wasserstein and Kalman-Wasserstein KL divergences give closed-form, finite control regularizers that keep LQR feedback nonzero in low-noise limits where classical KL regularization fails.

  11. Convex relaxation approaches for high-dimensional optimal transport

    math.OC 2025-11 conditional novelty 6.0 of 10

    High-dimensional optimal transport cost can be approximated by semidefinite programs built from sparse local moments, with exponentially decaying error for Gaussian measures with sparse precision.

  12. Wasserstein normalized autoencoder for anomaly detection

    hep-ex 2025-10 conditional novelty 6.0 of 10

    A Wasserstein-distance-trained normalized autoencoder detects semivisible jets in simulated LHC events with AUCs around 0.69–0.77, outperforming standard and normalized autoencoders on a ttbar background.

  13. Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications

    cs.LG 2019-07 unverdicted novelty 6.0 of 10

    A scalable framework combining streaming graphs, topology computation, and topology-aware datacubes enables interactive analysis of high-dimensional functions in scientific ML applications.

  14. Local Bures-Wasserstein Transport: A Practical and Fast Mapping Approximation

    stat.ML 2019-06 unverdicted novelty 6.0 of 10

    A local Gaussian Bures-Wasserstein method approximates transport maps and barycenters, claimed to run 80x faster than kernel baselines while using fewer components.

  15. ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    ArcVQ-VAE adds spherical angular-margin regularization consisting of ball-bounded norms and arc-cosine margin loss to improve codebook utilization in VQ-VAE for image tasks.

  16. Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer

    q-bio.QM 2026-02 unverdicted novelty 5.0 of 10

    Quantum annealing combined with a Neural Hash Function lets generative models create molecules that are more drug-like than classical versions or the training set itself.

  17. Variational Sparse Paired Autoencoders (vsPAIR) for Inverse Problems and Uncertainty Quantification

    cs.LG 2026-02 conditional novelty 5.0 of 10

    vsPAIR couples a Gaussian VAE over observations with a spike-and-slab sparse VAE over the quantity of interest via a learned latent mapping, yielding fast inverse reconstructions whose active latent dimensions can be ...

  18. Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net

    cs.CV 2025-10 conditional novelty 5.0 of 10

    ABHFA-Net is a novel few-shot classification framework that models prototypes as distributions, applies spatial-channel attention, and uses Bhattacharyya-based contrastive loss, achieving state-of-the-art accuracies o...

  19. MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification

    cs.CV 2025-08 conditional novelty 5.0 of 10

    MorphGen uses supervised contrastive learning to align histopathology images with nuclear masks and applies SWA, reporting improved out-of-domain cancer classification accuracy on CAMELYON17, BCSS, and OCELOT.

  20. Information-Preserving CSI Feedback: Invertible Networks with Endogenous Quantization and Channel Error Mitigation

    eess.SP 2025-07 reject novelty 5.0 of 10

    InvCSINet uses an invertible neural network with learned quantization and bit-channel distortion modules for FDD massive MIMO CSI feedback, but the claimed information-preserving guarantee rests on flawed proofs and a...

  21. From Points to Spheres: A Geometric Reinterpretation of Variational Autoencoders

    cs.LG 2025-07 conditional novelty 4.0 of 10

    The paper claims that KL-induced compactness, not stochasticity, is the key to VAE generative capability, supported by new latent-space uniformity metrics and codebook regularizer experiments.

  22. ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification

    cs.CV 2025-09 reject novelty 3.0 of 10

    ANROT-HELANet combines Hellinger aggregation, attention, and FGSM/Gaussian robust training for few-shot classification, but its ELBO derivation is invalid and its performance claims are overstated.

Pith tools