English
Related papers

Related papers: Amortized In-Context Mixed Effect Transformer Mode…

200 papers

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

Bayesian inference provides a natural way of incorporating prior beliefs and assigning a probability measure to the space of hypotheses. Current solutions rely on iterative routines like Markov Chain Monte Carlo (MCMC) sampling and…

Machine Learning · Computer Science 2025-02-11 Sarthak Mittal , Niels Leif Bracher , Guillaume Lajoie , Priyank Jaini , Marcus Brubaker

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

Structural Causal Models (SCMs) offer a principled framework to reason about interventions and support out-of-distribution generalization, which are key goals in scientific discovery. However, the task of learning SCMs from observed data…

Machine Learning · Computer Science 2026-04-06 Divyat Mahajan , Jannes Gladrow , Agrin Hilmkil , Cheng Zhang , Meyer Scetbon

Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision. Transformer-based neural processes and their variants are leading models for probabilistic meta-learning with a…

Machine Learning · Statistics 2025-03-06 Paul E. Chang , Nasrulloh Loka , Daolang Huang , Ulpu Remes , Samuel Kaski , Luigi Acerbi

Since the turn of the century, approximate Bayesian inference has steadily evolved as new computational techniques have been incorporated to handle increasingly complex and large-scale predictive problems. The recent success of deep neural…

Machine Learning · Statistics 2026-01-14 Roy Shivam Ram Shreshtth , Arnab Hazra , Gourab Mukherjee

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…

Machine Learning · Computer Science 2020-08-31 Ekaterina Iakovleva , Jakob Verbeek , Karteek Alahari

Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or neuroscience, increasingly leveraging modern generative methods like diffusion models to map…

As models of cognition grow in complexity and number of parameters, Bayesian inference with standard methods can become intractable, especially when the data-generating model is of unknown analytic form. Recent advances in simulation-based…

Machine Learning · Statistics 2020-07-14 Stefan T. Radev , Andreas Voss , Eva Marie Wieschen , Paul-Christian Bürkner

Bayesian inference often faces a trade-off between computational speed and sampling accuracy. We propose an adaptive workflow that integrates rapid amortized inference with gold-standard MCMC techniques to achieve a favorable combination of…

Machine Learning · Computer Science 2026-02-19 Chengkun Li , Aki Vehtari , Paul-Christian Bürkner , Stefan T. Radev , Luigi Acerbi , Marvin Schmitt

Finite mixtures are a broad class of models useful in scenarios where observed data is generated by multiple distinct processes but without explicit information about the responsible process for each data point. Estimating Bayesian mixture…

Machine Learning · Statistics 2026-03-17 Šimon Kucharský , Paul Christian Bürkner

We introduce a flexible, scalable Bayesian inference framework for nonlinear dynamical systems characterised by distinct and hierarchical variability at the individual, group, and population levels. Our model class is a generalisation of…

Machine Learning · Statistics 2019-10-03 Geoffrey Roeder , Paul K. Grant , Andrew Phillips , Neil Dalchau , Edward Meeds

Variational autoencoders (VAEs) rely on amortized variational inference to enable efficient posterior approximation, but this efficiency comes at the cost of a shared parametrization, giving rise to the amortization gap. We propose the…

Machine Learning · Computer Science 2026-04-21 Andrea Pollastro , Andrea Apicella , Francesco Isgrò , Roberto Prevete

We develop methods for efficient amortized approximate Bayesian inference over posterior distributions of probabilistic clustering models, such as Dirichlet process mixture models. The approach is based on mapping distributed,…

Machine Learning · Statistics 2018-11-27 Ari Pakman , Liam Paninski

Boundary condition tuning is a fundamental step in patient-specific cardiovascular modeling. Despite an increase in offline training cost, recent methods in data-driven variational inference can efficiently estimate the joint posterior…

Machine Learning · Computer Science 2026-03-23 Chloe H. Choi , Alison L. Marsden , Daniele E. Schiavazzi

Mixed-effects models are fundamental tools for analyzing clustered and repeated-measures data, but existing high-dimensional methods largely focus on penalized estimation with vector-valued covariates. Bayesian alternatives in this regime…

Methodology · Statistics 2026-02-24 Sreya Sarkar , Kshitij Khare , Sanvesh Srivastava

Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise…

Computer Vision and Pattern Recognition · Computer Science 2023-07-13 Ahmed Ghorbel , Wassim Hamidouche , Luce Morin

In this paper, we introduce \texttt{IAFormer}, a novel Transformer-based architecture that efficiently integrates pairwise particle interactions through a dynamic sparse attention mechanism. \texttt{IAFormer} has two new mechanisms within…

High Energy Physics - Phenomenology · Physics 2026-04-21 W. Esmail , A. Hammad , M. Nojiri

In structurally constrained molecular optimization, state-of-the-art methods restart an expensive oracle-driven search from scratch for every new input structure, scaling poorly to settings with many starting structures or expensive…

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential…

‹ Prev 1 2 3 10 Next ›