Iterative Amortized Hierarchical VAE

2026-01-22 · Simon W. Penninga, Ruud J. G. van Sloun arxiv

In this paper we propose the Iterative Amortized Hierarchical Variational Autoencoder (IA-HVAE), which expands on amortized inference with a hybrid scheme containing an initial amortized guess and iterative refinement with decoder gradients. We achieve this by creating a linearly separable decoder in a transform domain (e.g. Fourier space), enabling real-time applications with very high model depths. The architectural change leads to a 35x speed-up for iterative inference with respect to the traditional HVAE. We show that our hybrid approach outperforms fully amortized and fully iterative equivalents in accuracy and speed respectively. Moreover, the IAHVAE shows improved reconstruction quality over a vanilla HVAE in inverse problems such as deblurring and denoising.

📄 PDF Abstract BibTeX arXiv:2601.15894

Code (0)

등록된 구현이 없습니다.

Accelerating Hierarchical Sparse Predictive Coding with Hybrid Amortized Inference

2026-06-26 · Kazuhisa Fujita arxiv

Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while sparse coding imposes parsimonious latent representations through explic…

Iterative Amortized Policy Optimization

2020-10-20 · NeurIPS 2021 12 · Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo, Yisong Yue

Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the variational inference perspective on RL, p…

continuous-control Continuous Control Deep Reinforcement Learning reinforcement-learning+2

ASPIRE: Iterative Amortized Posterior Inference for Bayesian Inverse Problems

2024-05-08 · Rafael Orozco, Ali Siahkoohi, Mathias Louboutin, Felix J. Herrmann

Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intra…

Uncertainty Quantification Variational Inference

Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations

2021-06-07 · Patrick Emami, Pan He, Sanjay Ranka, Anand Rangarajan

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations …

Disentanglement Object Representation Learning

Recursive Inference for Variational Autoencoders

2020-11-17 · NeurIPS 2020 12 · Minyoung Kim, Vladimir Pavlovic

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amorti…

Variational Inference