MSE-optimal multi-step forecasters cannot match the marginal distribution of realizations under nonzero conditional uncertainty, creating a quantifiable accuracy-realism Pareto frontier across benchmarks.
Unrolled generative adversarial networks
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
We introduce a method to stabilize Generative Adversarial Networks (GANs) by defining the generator objective with respect to an unrolled optimization of the discriminator. This allows training to be adjusted between using the optimal discriminator in the generator's objective, which is ideal but infeasible in practice, and using the current value of the discriminator, which is often unstable and leads to poor solutions. We show how this technique solves the common problem of mode collapse, stabilizes training of GANs with complex recurrent generators, and increases diversity and coverage of the data distribution by the generator.
citation-role summary
other 1
citation-polarity summary
roles
other 1polarities
unclear 1representative citing papers
Progressive growing stabilizes GAN training to produce high-resolution images of unprecedented quality and achieves a record unsupervised inception score of 8.80 on CIFAR10.
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
PEAR computes regret gradients via tangent-space projection of prediction error, delivering top decision quality and efficiency on LP and QP tasks without solver differentiation.
SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.
citing papers explorer
-
Expectations vs. Realities: The Cost of MSE-Optimal Forecasting Under Conditional Uncertainty
MSE-optimal multi-step forecasters cannot match the marginal distribution of realizations under nonzero conditional uncertainty, creating a quantifiable accuracy-realism Pareto frontier across benchmarks.
-
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive growing stabilizes GAN training to produce high-resolution images of unprecedented quality and achieves a record unsupervised inception score of 8.80 on CIFAR10.
-
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
Recursive generative retraining with heterogeneous rewards converges to a stable distribution satisfying a weighted Nash bargaining solution, preserving diversity under stated conditions.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
Decision-Focused Learning via Tangent-Space Projection of Prediction Error
PEAR computes regret gradients via tangent-space projection of prediction error, delivering top decision quality and efficiency on LP and QP tasks without solver differentiation.
-
SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.