res_ffca3074All 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)
arXiv 1701.07875 · stat.ML cs.LG
Read on arXiv · arXiv non-exclusive license
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.
res_ffca3074All 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)
clm_4228b71cFinally, 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)
clm_d1e9a19fIn 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)
res_caba1e9aFurthermore, 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)
res_8050037dWe 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)
clm_d78634f2In 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.
clm_ac396273We 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).
clm_ca493519First, we prove that there exists an optimal discriminator.
clm_3f7a23f9This is a long known fact, found for example in [22], but we prove it later for completeness.
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.