MearcAll papers

arXiv 1701.07875 · stat.ML cs.LG

Wasserstein GAN

Martin Arjovsky, Soumith Chintala, Léon Bottou

Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.

No reproduction recordedres_ffca3074
All training curves were passed through the same median filter as in Figure 3. to stare at the generated samples to figure out failure modes and to gain information on … (excerpt)

Meaningful loss metric · page 11 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_4228b71c
Finally, as a negative result, we report that WGAN training becomes unstable at times when one uses a momentum based optimizer such as Adam [8] (with β1 > 0) on … (excerpt)

Meaningful loss metric · page 12 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_d1e9a19f
In this new model, we showed that we can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and … (excerpt)

Conclusion · page 16 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_caba1e9a
Furthermore, by assumption 1, we can define L(θ) = Ez[L(θ,z )] and achieve |W (Pr, Pθ)−W (Pr, Pθ′)|≤ W (Pθ, Pθ′)≤L(θ)‖θ−θ′‖ 20 for all θ′∈Uθ, meaning that W (Pr, Pθ) … (excerpt)

Proofs of things · page 20 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_8050037d
We can now show KL(P‖Pm) = ∫ log(gn) dP ≤ log(1 +ϵ) + ∫ Bn log(gn) dP ≤ log(1 +ϵ) + log(3)P(Bn) so we achieve 0≤ lim supKL(P‖Pm)≤ log(1+ϵ) and … (excerpt)

Proofs of things · page 23 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_d78634f2
In this appendix we show that under an optimal discriminator, energy-based GANs (EBGANs) [25] optimize the total variation distance between the real and generated distributions.

Energy-based GANs optimize total variation · page 26 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_ac396273
We show that such a discriminator always exists for any two distributions Pr and Pθ, and that under such a discriminator,LG(D∗,gθ) is proportional to δ(Pr, Pθ).

Energy-based GANs optimize total variation · page 26 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_ca493519
First, we prove that there exists an optimal discriminator.

Energy-based GANs optimize total variation · page 26 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_3f7a23f9
This is a long known fact, found for example in [22], but we prove it later for completeness.

Energy-based GANs optimize total variation · page 27 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1701.07875) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.