We propose Amortized Posterior Sampling (APS), a novel variational inference approach for efficient posterior sampling in inverse problems. Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model. This results in a powerful, amortized sampler capable of generating diverse posterior samples with a single neural function evaluation, generalizing across various measurements. Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains. We demonstrate its effectiveness on a range of tasks, including image restoration, manifold signal reconstruction, and climate data imputation. APS significantly outperforms existing approaches in computational efficiency while maintaining competitive reconstruction quality, enabling real-time, high-quality solutions to inverse problems across diverse domains.
Samsung AI Center（三星人工智能中心）；Rutgers University（罗格斯大学）
Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the cost of degraded accuracy in posterior approximation, often underperforming the instance-wise variational optimization. Although the latest semi-amortized approaches mitigate the issue by performing a few variational optimization updates starting from the VAE's amortized inference output, they inherently suffer from computational overhead for inference at test …
Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. However, such amortized variational inference faces two challenges: (1) the limited posterior expressiveness of fully-factorized Gaussian assumption and (2) the amortization error of the inference model. We present a novel approach that addresses both challenges. First, we focus on ReLU networks with Gaussian output and illustrate their connection to probabilistic PCA. Building on this observation, we derive an iterative algorithm that finds the mode of the posterior and apply full-co…
California Institute of Technology（加州理工学院）；Disney Research（迪士尼研究院）
Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computationally efficient. However, standard inference models are restricted to direct mappings from data to approximate posterior estimates. The failure of these models to reach fully optimized approximate posterior estimates results in an amortization gap. We aim toward closing this gap …
Instance-Adaptive Parametrization for Amortized Variational Inference
Department of Electrical Engineering and Information Technology, University of Naples Federico II（那不勒斯费德里科二世大学电气工程与信息技术系）；Department of Information Engineering, Electrical Engineering, and Applied Mathematics, University of Salerno（萨勒诺大学信息工程、电气工程与应用数学系）
Samsung AI Center（三星人工智能中心）；Rutgers University（罗格斯大学）
Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were proposed to address this drawback; however, their iterative gradient update procedures can be computationally demanding. To address these issues, in this paper we introduce an accurate amortized inference algorithm. We propose a novel recursive mixture estimation algorithm for VAEs that iteratively augments the current mixture with new components so as to ma…
Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable Models
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Imperial College London（帝国理工学院）；University of Technology Nuremberg (UTN)（纽伦堡工业大学）；Helmholtz AI（亥姆霍兹人工智能中心）；Xyme
University of Toronto（多伦多大学）；Vector Institute（向量研究所）
Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing samples from the BNN posterior using mini-batches. However, SGLD and its extensions require storage of many copies of the model parameters, a potentially prohibitive cost, especially for large neural networks. We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN). At test-time, samples are generated by the GAN. We show that this distillation …
Harvard University（哈佛大学）；Massachusetts Institute of Technology（麻省理工学院）
Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE), recent empirical work suggests that inference networks can produce suboptimal variational parameters. We propose a hybrid approach, to use AVI to initialize the variational parameters and run stochastic variational inference (SVI) to refine them. Crucially, the local SVI procedure is itself differentiable, so the inference network and generative model can be trained end-to-end…
Centre for Cognitive Science, Technical University Darmstadt（达姆施塔特工业大学认知科学中心）；DeepMind；research center caesar, an associate of the Max Planck Society（凯撒研究中心，马克斯·普朗克学会合作机构）；IMPRS Brain and Behavior Bonn/Florida（波恩/佛罗里达国际马克斯·普朗克脑与行为研究学院）；HHMI Janelia Research Campus（霍华德·休斯医学研究所珍妮莉亚研究园区）；Columbia University（哥伦比亚大学）
Calcium imaging permits optical measurement of neural activity. Since intracellular calcium concentration is an indirect measurement of neural activity, computational tools are necessary to infer the true underlying spiking activity from fluorescence measurements. Bayesian model inversion can be used to solve this problem, but typically requires either computationally expensive MCMC sampling, or faster but approximate maximum-a-posteriori optimization. Here, we introduce a flexible algorithmic framework for fast, efficient and accurate extraction of neural spikes from imaging data. Using the f…
Frequently, population studies feature pyramidally-organized data represented using Hierarchical Bayesian Models (HBM) enriched with plates. These models can become prohibitively large in settings such as neuroimaging, where a sample is composed of a functional MRI signal measured on 300 brain locations, across 4 measurement sessions, and 30 subjects, resulting in around 1 million latent parameters.Such high dimensionality hampers the usage of modern, expressive flow-based techniques.To infer parameter posterior distributions in this challenging class of problems, we designed a novel methodolo…
Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；European XFEL（欧洲X射线自由电子激光器）；University of Siegen（锡根大学）；Forschungszentrum Jülich（于利希研究中心）
Grazing-Incidence Small-Angle X-ray Scattering (GISAXS) is a modern imaging technique used in material research to study nanoscale materials. Reconstruction of the parameters of an imaged object imposes an ill-posed inverse problem that is further complicated when only an in-plane GISAXS signal is available. Traditionally used inference algorithms such as Approximate Bayesian Computation (ABC) rely on computationally expensive scattering simulation software, rendering analysis highly time-consuming. We propose a simulation-based framework that combines variational auto-encoders and normalizing…
Stellenbosch University（斯泰伦博斯大学）；National Institute for Theoretical and Computational Sciences（国家理论与计算科学研究所）
Initial work on variational autoencoders assumed independent latent variables with simple distributions. Subsequent work has explored incorporating more complex distributions and dependency structures: including normalizing flows in the encoder network allows latent variables to entangle non-linearly, creating a richer class of distributions for the approximate posterior, and stacking layers of latent variables allows more complex priors to be specified for the generative model. This work explores incorporating arbitrary dependency structures, as specified by Bayesian networks, into VAEs. This…
Stochastic Transition-Map Distillation for Fast Probabilistic Inference
Department of Aerospace Engineering, Georgia Institute of Technology（佐治亚理工学院航空航天工程系）；Department of Computer Science, Georgia Institute of Technology（佐治亚理工学院计算机科学系）；Department of Mathematics, Florida State University（佛罗里达州立大学数学系）
FalconBC: Flow matching for Amortized inference of Latent-CONditioned physiologic Boundary Conditions
Department of Mechanical Engineering, Stanford University（斯坦福大学机械工程系）；Institute for Computational and Mathematical Engineering, Stanford University（斯坦福大学计算与数学工程研究所）；Bioengineering, Stanford University（斯坦福大学生物工程系）；Pediatric Cardiology, Stanford University（斯坦福大学儿科心脏病学）；Department of Applied and Computational Mathematics and Statistics, University of Notre Dame（诺丁汉大学应用与计算数学与统计学系）
ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding
University of Oxford（牛津大学）；Harvard University（哈佛大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）；Vector Institute（向量研究所）；University College London（伦敦大学学院）
PriorGuide: Test-Time Prior Adaptation for Simulation-Based Inference
Department of Computer Science, University of Helsinki, Finland（赫尔辛基大学计算机科学系，芬兰）；ELLIS Institute Finland（芬兰ELLIS研究所）；Department of Computer Science, Aalto University, Finland（芬兰阿尔托大学计算机科学系）
The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for efficient inference, focusing on mean-field or other simple structured approximations. This restriction has a significant impact on the quality of inferences made using variational methods. We introduce a new approach for specifying flexible, arbitrarily complex and scalable approximate posterior distributions. Our approximations are distributions constructed through a normalizi…
Amortized Filtering and Smoothing with Conditional Normalizing Flows
School of Mathematics and Statistics（数学与统计学学院）；The University of Sydney（悉尼大学）；Faculty of Science and Technology（科学与技术学院）；Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist大学）；Institute of Computational Mathematics and Scientific/Engineering Computing（计算数学与科学/工程计算研究所）；Academy of Mathematics and Systems Science（数学与系统科学学院）；Chinese Academy of Sciences（中国科学院）；Department of Mathematics and Center for Computation and Technology（数学系与计算技术中心）；Louisiana State University（路易斯安那州立大学）
Rice University（莱斯大学）；Aix-Marseille Univ（艾克斯-马赛大学）；Université de Toulon（土伦大学）；CNRS（法国国家科学研究中心）
Deep Generative Networks (DGNs) with probabilistic modeling of their output and latent space are currently trained via Variational Autoencoders (VAEs). In the absence of a known analytical form for the posterior and likelihood expectation, VAEs resort to approximations, including (Amortized) Variational Inference (AVI) and Monte-Carlo (MC) sampling. We exploit the Continuous Piecewise Affine (CPA) property of modern DGNs to derive their posterior and marginal distributions as well as the latter's first moments. These findings enable us to derive an analytical Expectation-Maximization (EM) algo…
A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized inference distributions and, in some cases, improving the objective provably degrades the inference quality. In addition, it has been observed that variational autoencoders tend to ignore the latent variables when combined with a decoding distribution that is too flexible. We again identify the cause in existing training criteria and propose a new class of obj…
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in considerable additional error called the amortization gap. To close the amortization gap and improve the training of the generative model, recent works have introduced an additional refinement step that applies stochastic variational inference (SVI) to improve upon the variational par…
StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
Institute of Astronomy（天文研究所）；Kavli Institute for Cosmology, University of Cambridge, Cambridge, UK（剑桥大学卡文迪许实验室，剑桥，英国）；Research Computing Services, University of Cambridge, Cambridge, UK（剑桥大学研究计算服务）；The Oskar Klein Centre, Department of Physics, Stockholm University, Stockholm, SE（斯德哥尔摩大学物理系奥斯卡·克莱因中心）；Cavendish Laboratory, Department of Physics, University of Cambridge, Cambridge, UK（剑桥大学物理系卡文迪许实验室）
We propose a novel amortized variational inference scheme for an empirical Bayes meta-learning model, where model parameters are treated as latent variables. We learn the prior distribution over model parameters conditioned on limited training data using a variational autoencoder approach. Our framework proposes sharing the same amortized inference network between the conditional prior and variational posterior distributions over the model parameters. While the posterior leverages both the labeled support and query data, the conditional prior is based only on the labeled support data. We show …
U-DAVI: Uncertainty-Aware Diffusion-Prior-Based Amortized Variational Inference for Image Reconstruction
Computing and Mathematical Sciences, California Institute of Technology（计算与数学科学系，加州理工学院）；Mathematical Sciences, California Institute of Technology（数学科学系，加州理工学院）
