Pith. sign in

REVIEW 14 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 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 194 citations worldwide. Full citation record

  1. Minimax Optimal Rates for Regression on Manifolds and Distributions

    math.ST 2025-06 accept novelty 7.0 of 10

    Minimax rates for conditional distribution estimation on manifolds are established, with matching upper bounds from a hybrid wavelet and manifold estimator.

  2. Neural Estimation for Scaling Entropic Multimarginal Optimal Transport

    cs.LG 2025-05 conditional novelty 7.0 of 10

    NEMOT uses neural dual potentials trained on mini-batches to estimate entropic multimarginal optimal transport costs and plans, with non-asymptotic error guarantees and orders-of-magnitude speedups over Sinkhorn.

  3. $\mathbf{\lambda}$-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.

  4. 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.

  5. 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.

  6. 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.

  7. Imaging 3D polarization dynamics via deep learning 4D-STEM

    cond-mat.mtrl-sci 2025-06 conditional novelty 6.0 of 10

    A deep learning framework with domain adaptation reconstructs 3D polarization vectors from 4D-STEM data, showing that BST polarization switching involves rotation toward <111> energy minima and topological protection.

  8. 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 ...

  9. 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.

  10. 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...

  11. Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis

    cs.LG 2025-06 reject novelty 5.0 of 10

    The authors derive information-theoretic generalization bounds for VAEs and diffusion models that expose a trade-off in the diffusion time T, and propose using the computable bound to select T and regularize training.

  12. 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.

  13. Joint-stochastic-approximation Autoencoders with Application to Semi-supervised Learning

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A stochastic-approximation autoencoder that maximizes the true log-likelihood and uses MCMC-corrected posterior sampling is applied to semi-supervised learning with discrete latent codes, reporting useful but not stat...

  14. 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