English
Related papers

Related papers: Amortized Variational Deep Q Network

200 papers

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

Machine Learning · Computer Science 2025-10-14 Sarthak Mittal , Divyat Mahajan , Guillaume Lajoie , Mohammad Pezeshki

Optimization is a ubiquitous modeling tool and is often deployed in settings which repeatedly solve similar instances of the same problem. Amortized optimization methods use learning to predict the solutions to problems in these settings,…

Machine Learning · Computer Science 2025-10-07 Brandon Amos

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 training an…

Machine Learning · Computer Science 2023-05-25 Manuel Glöckler , Michael Deistler , Jakob H. Macke

Our work utilized a non-sequential simulation-based inference algorithm to provide an amortized neural density estimator, which approximates the posterior distribution for seven parameters of the adaptive exponential integrate-and-fire…

Neural and Evolutionary Computing · Computer Science 2026-02-13 Jakob Kaiser , Eric Müller , Johannes Schemmel

Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unseen models typically requires retraining or costly test-time finetuning. In this paper,…

Machine Learning · Computer Science 2026-05-27 Joohwan Ko , Justin Domke

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…

Machine Learning · Statistics 2018-07-25 Yoon Kim , Sam Wiseman , Andrew C. Miller , David Sontag , Alexander M. Rush

Inferring causal structure poses a combinatorial search problem that typically involves evaluating structures with a score or independence test. The resulting search is costly, and designing suitable scores or tests that capture prior…

Machine Learning · Computer Science 2022-12-16 Lars Lorch , Scott Sussex , Jonas Rothfuss , Andreas Krause , Bernhard Schölkopf

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…

Machine Learning · Statistics 2019-01-10 Rui Shu , Hung H. Bui , Shengjia Zhao , Mykel J. Kochenderfer , Stefano Ermon

Inverse problems, i.e., estimating parameters of physical models from experimental data, are ubiquitous in science and engineering. The Bayesian formulation is the gold standard because it alleviates ill-posedness issues and quantifies…

Machine Learning · Statistics 2024-05-28 Sharmila Karumuri , Ilias Bilionis

In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its…

Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations. Notwithstanding, the existing optimization approaches use gradient…

Machine Learning · Computer Science 2023-01-31 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

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, current…

Machine Learning · Computer Science 2024-07-16 Manuel Gloeckler , Michael Deistler , Christian Weilbach , Frank Wood , Jakob H. Macke

In a probabilistic latent variable model, factorized (or mean-field) variational inference (F-VI) fits a separate parametric distribution for each latent variable. Amortized variational inference (A-VI) instead learns a common inference…

Machine Learning · Statistics 2024-05-27 Charles C. Margossian , David M. Blei

We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This approach allows for the efficient inference of theoretical parameters in high-dimensional…

Machine Learning · Computer Science 2026-02-23 Rajneil Baruah

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors in downstream tasks poses an intractable posterior inference problem. This paper studies amortized…

Learned image reconstruction techniques using deep neural networks have recently gained popularity, and have delivered promising empirical results. However, most approaches focus on one single recovery for each observation, and thus neglect…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Chen Zhang , Riccardo Barbano , Bangti Jin

Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it remains unclear how to jointly learn reward functions from heterogeneous feedback types such as…

Machine Learning · Computer Science 2026-02-18 Raphaël Baur , Yannick Metz , Maria Gkoulta , Mennatallah El-Assady , Giorgia Ramponi , Thomas Kleine Buening

Safe active learning (AL) is a sequential scheme for learning unknown systems while respecting safety constraints during data acquisition. Existing methods often rely on Gaussian processes (GPs) to model the task and safety constraints,…

Machine Learning · Computer Science 2026-04-07 Cen-You Li , Marc Toussaint , Barbara Rakitsch , Christoph Zimmer

Bayesian inference is a powerful tool for parameter estimation and uncertainty quantification in dynamical systems. However, for nonlinear oscillator networks such as Kuramoto models, widely used to study synchronization phenomena in…

Applications · Statistics 2026-03-24 Emma Hannula , Jana de Wiljes , Matthew T. Moores , Heikki Haario , Lassi Roininen

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, policy networks, when…

Machine Learning · Computer Science 2021-10-26 Joseph Marino , Alexandre Piché , Alessandro Davide Ialongo , Yisong Yue