FIS-GAN: GAN with Flow-based Importance Sampling
Generative Adversarial Networks (GAN) training process, in most cases, apply Uniform or Gaussian sampling methods in the latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic optimization in supervised learning by prioritizing training examples. In this paper, we explore the possibility of adapting importance sampling into adversarial learning. We use importance sampling to replace Uniform and Gaussian sampling methods in the latent space and employ normalizing flow to approximate latent space posterior distribution by density estimation. Empirically, results on MNIST and Fashion-MNIST demonstrate that our method significantly accelerates GAN's optimization while retaining visual fidelity in generated samples.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationStochastic OptimizationSimilar Papers 제목 키워드 기반
Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows
Importance sampling is a rare event simulation technique used in Monte Carlo simulations to bias the sampling distribution towards the rare event of interest. By assigning appropriate weights to sampled points, importanc…
Autonomous RacingCollision AvoidanceScore-Regularized Joint Sampling with Importance Weights for Flow Matching
Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-varia…
TFTF: Training-Free Targeted Flow for Conditional Sampling
We propose a training-free conditional sampling method for flow matching models based on importance sampling. Because a naïve application of importance sampling suffers from weight degeneracy in high-dimensional settings…
Text-to-Image GenerationFlow Annealed Importance Sampling Bootstrap meets Differentiable Particle Physics
High-energy physics requires the generation of large numbers of simulated data samples from complex but analytically tractable distributions called matrix elements. Surrogate models, such as normalizing flows, are gainin…
Computational EfficiencyFALCON: Few-step Accurate Likelihoods for Continuous Flows
Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann Generators tackle this problem by pairing a generative model, capable of exact likelihood …