paper-with-me

Papers

Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriors

2024-01-05 · Wasu Top Piriyakulkij, Yingheng Wang, Volodymyr Kuleshov

We propose denoising diffusion variational inference (DDVI), a black-box variational inference algorithm for latent variable models which relies on diffusion models as flexible approximate posteriors. Specifically, our method introduces an expressive class of diffusion-based variational posteriors that perform iterative refinement in latent space; we train these posteriors with a novel regularized evidence lower bound (ELBO) on the marginal likelihood inspired by the wake-sleep algorithm. Our method is easy to implement (it fits a regularized extension of the ELBO), is compatible with black-box variational inference, and outperforms alternative classes of approximate posteriors based on normalizing flows or adversarial networks. We find that DDVI improves inference and learning in deep latent variable models across common benchmarks as well as on a motivating task in biology -- inferring latent ancestry from human genomes -- where it outperforms strong baselines on the Thousand Genomes dataset.

📄 PDF Abstract BibTeX arXiv:2401.02739

Code (1)

topwasu/ddvi 공식 구현 pytorch

Tasks

DenoisingVariational Inference

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Diffusion Bridge Variational Inference for Deep Gaussian Processes

2025-09-23 · Jian Xu, Qibin Zhao, John Paisley, Delu Zeng arxiv

Deep Gaussian processes (DGPs) enable expressive hierarchical Bayesian modeling but pose substantial challenges for posterior inference, especially over inducing variables. Denoising diffusion variational inference (DDVI…

Image ReconstructionGaussian Processes

Variational Distillation of Diffusion Policies into Mixture of Experts

2024-06-18 · Hongyi Zhou, Denis Blessing, Ge Li, Onur Celik 외

This work introduces Variational Diffusion Distillation (VDD), a novel method that distills denoising diffusion policies into Mixtures of Experts (MoE) through variational inference. Diffusion Models are the current stat…

DenoisingMixture-of-ExpertsVariational Inference

Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning

2025-11-19 · Yuxuan Gu, Weimin Bai, Yifei Wang, Weijian Luo 외 arxiv

Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR suffers from slow inference due …

Reinforcement Learning

Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference

2024-07-24 · Jian Xu, Delu Zeng, John Paisley

Deep Gaussian processes (DGPs) provide a robust paradigm for Bayesian deep learning. In DGPs, a set of sparse integration locations called inducing points are selected to approximate the posterior distribution of the mod…

DenoisingGaussian ProcessesVariational Inference

Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration

2023-10-26 · NeurIPS 2023 11 · Longlin Yu, Tianyu Xie, Yu Zhu, Tong Yang 외

Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner. However, the single-layer architec…

Bayesian InferenceVariational Inference