clm_ace044a3We 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)
arXiv 1406.2661 · 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.
clm_ace044a3We 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)
clm_d30be011We propose a new generative model estimation procedure that sidesteps these difficulties.
res_914bd31fIn 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.
res_35873857Therefore, we would like Algorithm 1 to converge to a good estimator ofpdata, if given enough capacity and training time.
res_29ca143cAt that point,C(G) achieves the value− log 4.
res_71f2e3c8We 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)
res_57f1a293IfG 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)
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.