MearcAll papers

arXiv 1406.2661 · stat.ML cs.LG

Generative Adversarial Networks

Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, and 2 more

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 recordedclm_ace044a3
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and … (excerpt)

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_d30be011
We propose a new generative model estimation procedure that sidesteps these difficulties.

Introduction · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_914bd31f
In this case, we can train both models using only the highly successful backpropagation and dropout algorithms [17] and sample from the generative model using only forward propagation.

Introduction · page 2 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_35873857
Therefore, we would like Algorithm 1 to converge to a good estimator ofpdata, if given enough capacity and training time.

Theoretical Results · page 3 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_29ca143c
At that point,C(G) achieves the value− log 4.

Theoretical Results · page 5 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_71f2e3c8
We recognize in the previous expression the Jensen– Shannon divergence between the model’s distribution and the data generating process: C(G) =− log(4) + 2·JSD (pdata‖pg ) (6) Since the Jensen–Shannon … (excerpt)

Theoretical Results · page 5 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_57f1a293
IfG andD have enough capacity, and at each step of Algorithm 1, the discriminator is allowed to reach its optimum givenG, andpg is updated so as to improve the criterion … (excerpt)

Convergence of Algorithm 1 · page 5 · 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 (1406.2661) 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.