DriftXpress approximates drifting kernels via projected RKHS fields to lower training cost of one-step generative models while matching original FID scores.
Training gener- ative neural networks via maximum mean discrepancy optimization.arXiv preprint arXiv:1505.03906
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
We consider training a deep neural network to generate samples from an unknown distribution given i.i.d. data. We frame learning as an optimization minimizing a two-sample test statistic---informally speaking, a good generator network produces samples that cause a two-sample test to fail to reject the null hypothesis. As our two-sample test statistic, we use an unbiased estimate of the maximum mean discrepancy, which is the centerpiece of the nonparametric kernel two-sample test proposed by Gretton et al. (2012). We compare to the adversarial nets framework introduced by Goodfellow et al. (2014), in which learning is a two-player game between a generator network and an adversarial discriminator network, both trained to outwit the other. From this perspective, the MMD statistic plays the role of the discriminator. In addition to empirical comparisons, we prove bounds on the generalization error incurred by optimizing the empirical MMD.
representative citing papers
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.
Mixture-of-experts flow matching enables non-autoregressive language models to achieve autoregressive-level quality in three sampling steps, delivering up to 1000x faster inference than diffusion models.
A stochastic MPC controller for HCCI engines using learned uncertainty distributions, polynomial chaos expansion, and an MMD-based cost reduces combustion phasing variation by over 28% and improves load tracking by over 26% in simulations compared to standard methods.
citing papers explorer
-
DriftXpress: Faster Drifting Models via Projected RKHS Fields
DriftXpress approximates drifting kernels via projected RKHS fields to lower training cost of one-step generative models while matching original FID scores.
-
Demystifying MMD GANs
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.
-
Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching
Mixture-of-experts flow matching enables non-autoregressive language models to achieve autoregressive-level quality in three sampling steps, delivering up to 1000x faster inference than diffusion models.
-
Nonlinear Stochastic Model Predictive Control with Generative Uncertainty in Homogeneous Charge Compression Ignition
A stochastic MPC controller for HCCI engines using learned uncertainty distributions, polynomial chaos expansion, and an MMD-based cost reduces combustion phasing variation by over 28% and improves load tracking by over 26% in simulations compared to standard methods.