paper-with-me

Papers

Amortized Inference Regularization

2018-05-23 · NeurIPS 2018 12 · Rui Shu, Hung H. Bui, Shengjia Zhao, Mykel J. Kochenderfer, Stefano Ermon

The variational autoencoder (VAE) is a popular model for density estimation and representation learning. Canonically, the variational principle suggests to prefer an expressive inference model so that the variational approximation is accurate. However, it is often overlooked that an overly-expressive inference model can be detrimental to the test set performance of both the amortized posterior approximator and, more importantly, the generative density estimator. In this paper, we leverage the fact that VAEs rely on amortized inference and propose techniques for amortized inference regularization (AIR) that control the smoothness of the inference model. We demonstrate that, by applying AIR, it is possible to improve VAE generalization on both inference and generative performance. Our paper challenges the belief that amortized inference is simply a mechanism for approximating maximum likelihood training and illustrates that regularization of the amortization family provides a new direction for understanding and improving generalization in VAEs.

📄 PDF Abstract BibTeX arXiv:1805.08913

Code (0)

등록된 구현이 없습니다.

Tasks

Density EstimationRepresentation Learning

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음
USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

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-controlContinuous ControlDeep Reinforcement Learningreinforcement-learning+2

Adversarial robustness of amortized Bayesian inference

2023-05-24 · Manuel Glöckler, Michael Deistler, Jakob H. Macke

Bayesian inference usually requires running potentially costly inference procedures separately for every new observation. In contrast, the idea of amortized Bayesian inference is to initially invest computational cost in…

Adversarial RobustnessBayesian Inference

Multi-objects Generation with Amortized Structural Regularization

2019-06-10 · NeurIPS 2019 12 · Kun Xu, Chongxuan Li, Jun Zhu, Bo Zhang

Deep generative models (DGMs) have shown promise in image generation. However, most of the existing work learn the model by simply optimizing a divergence between the marginal distributions of the model and the data, and…

Image Generation

Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification

2026-05-05 · Nan Feng, Xun Huan arxiv

Bayesian predictive inference propagates parameter uncertainty to quantities of interest through the posterior-predictive distribution. In practice, this is typically performed using a two-stage procedure: first approxim…

All-in-one simulation-based inference

2024-04-15 · Manuel Gloeckler, Michael Deistler, Christian Weilbach, Frank Wood 외

Amortized Bayesian inference trains neural networks to solve stochastic inference problems using model simulations, thereby making it possible to rapidly perform Bayesian inference for any newly observed data. However, c…

AllBayesian InferenceEpidemiology