Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
We present latent nonlinear denoising score matching (LNDSM), a novel training objective for score-based generative models that integrates nonlinear forward dynamics with the VAE-based latent SGM framework. This combination is achieved by reformulating the cross-entropy term using the approximate Gaussian transition induced by the Euler-Maruyama scheme. To ensure numerical stability, we identify and remove two zero-mean but variance exploding terms arising from small time steps. Experiments on variants of the MNIST dataset demonstrate that the proposed method achieves faster synthesis and enhanced learning of inherently structured distributions. Compared to benchmark structure-agnostic latent SGMs, LNDSM consistently attains superior sample quality and variability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Nonlinear denoising score matching for enhanced learning of structured distributions
We present a novel method for training score-based generative models which uses nonlinear noising dynamics to improve learning of structured distributions. Generalizing to a nonlinear drift allows for additional structur…
DenoisingRepresentation Learning in Continuous-Time Score-Based Generative Models
Score-based methods represented as stochastic differential equations on a continuous time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score match…
DenoisingRepresentation LearningDiffusion-Based Representation Learning
Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score m…
Denoisingimage-classificationImage ClassificationRepresentation Learning+1What's the score? Automated Denoising Score Matching for Nonlinear Diffusions
Reversing a diffusion process by learning its score forms the heart of diffusion-based generative modeling and for estimating properties of scientific systems. The diffusion processes that are tractable center on linear …
DenoisingLatent Target Score Matching, with an application to Simulation-Based Inference
Denoising score matching (DSM) for training diffusion models may suffer from high variance at low noise levels. Target Score Matching (TSM) mitigates this when clean data scores are available, providing a low-variance ob…