Pith Number

pith:2FGXYWYD

pith:2018:2FGXYWYDWCT3XWECO4BFZ5ZK6E

not attested not anchored not stored refs resolved

Demystifying MMD GANs

Arthur Gretton, Danica J. Sutherland, Michael Arbel, Miko{\l}aj Bi\'nkowski

Gradient estimators for MMD GANs and Wasserstein GANs are unbiased, but finite-sample discriminators bias the generator updates.

arxiv:1801.01401 v5 · 2018-01-04 · stat.ML · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{2FGXYWYDWCT3XWECO4BFZ5ZK6E}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We show that gradient estimators used in the optimization process for both MMD GANs and Wasserstein GANs are unbiased, but learning a discriminator based on samples leads to biased gradients for the generator parameters.

C2weakest assumption

The theoretical unbiasedness of the critic gradients holds under the assumption that the kernel is fixed and positive definite, and that the practical bias from finite samples does not dominate other optimization issues in real training.

C3one line summary

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.

References

62 extracted · 62 resolved · 39 Pith anchors

[1] arXiv preprint arXiv:1701.04862 , year= 2017 · arXiv:1701.04862

[2] Wasserstein GAN 2017 · arXiv:1701.07875

[3] Do GAN s actually learn the distribution? an empirical study 2017 · arXiv:1706.08224

[4] Generalization and Equilibrium in Generative Adversarial Nets (GANs) 2017 · arXiv:1703.00573

[5] Bellemare, Ivo Danihelka, Will Dabney, Shakir Mohamed, Balaji Lakshminarayanan, Stephan Hoyer, and R´emi Munos 2017 · arXiv:1705.10743

Formal links

1 machine-checked theorem link

Cited by

57 papers in Pith

GRE-Diff: Gaussian Room Embeddings for Structured Layout Diffusion

ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors

SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gaussian Splatting

Lighting-Consistent Object Transfer Across Radiance Fields

Receipt and verification

First computed	2026-05-17T23:39:05.168704Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d14d7c5b03b0a7bbd88277025cf72af1169c14156463487d5369739d8cc42e61

Aliases

arxiv: 1801.01401 · arxiv_version: 1801.01401v5 · doi: 10.48550/arxiv.1801.01401 · pith_short_12: 2FGXYWYDWCT3 · pith_short_16: 2FGXYWYDWCT3XWEC · pith_short_8: 2FGXYWYD

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/2FGXYWYDWCT3XWECO4BFZ5ZK6E \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: d14d7c5b03b0a7bbd88277025cf72af1169c14156463487d5369739d8cc42e61

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d2c6c23e9048f2e7f953dc43071d15ee896a0710d38fa54558867dd0f7438474",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2018-01-04T15:25:26Z",
    "title_canon_sha256": "fd2357f919bc86340dbd2aa08f818090f09a7efd61582570a969498869ebeaf0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1801.01401",
    "kind": "arxiv",
    "version": 5
  }
}