English
Related papers

Related papers: Interpolating between sampling and variational inf…

200 papers

We present Sequential Neural Variational Inference (SNVI), an approach to perform Bayesian inference in models with intractable likelihoods. SNVI combines likelihood-estimation (or likelihood-ratio-estimation) with variational inference to…

Machine Learning · Statistics 2022-10-20 Manuel Glöckler , Michael Deistler , Jakob H. Macke

Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even with model mismatch and adversaries. Unfortunately, exact Bayesian inference is rarely…

Machine Learning · Statistics 2020-08-03 Badr-Eddine Chérief-Abdellatif , Pierre Alquier , Mohammad Emtiyaz Khan

We develop stochastic variational inference, a scalable algorithm for approximating posterior distributions. We develop this technique for a large class of probabilistic models and we demonstrate it with two probabilistic topic models,…

Machine Learning · Statistics 2013-04-24 Matt Hoffman , David M. Blei , Chong Wang , John Paisley

Variational Bayesian inference and (collapsed) Gibbs sampling are the two important classes of inference algorithms for Bayesian networks. Both have their advantages and disadvantages: collapsed Gibbs sampling is unbiased but is also…

Machine Learning · Computer Science 2012-06-18 Max Welling , Yee Whye Teh , Hilbert Kappen

Geoscientists use observed data to estimate properties of the Earth's interior. This often requires non-linear inverse problems to be solved and uncertainties to be estimated. Bayesian inference solves inverse problems under a probabilistic…

Geophysics · Physics 2024-01-01 Xuebin Zhao , Andrew Curtis

Variational Inference (VI) is an attractive alternative to Markov Chain Monte Carlo (MCMC) due to its computational efficiency in the case of large datasets and/or complex models with high-dimensional parameters. However, evaluating the…

Machine Learning · Statistics 2023-02-27 Yu Wang , Mikołaj Kasprzak , Jonathan H. Huggins

Two popular classes of methods for approximate inference are Markov chain Monte Carlo (MCMC) and variational inference. MCMC tends to be accurate if run for a long enough time, while variational inference tends to give better approximations…

Machine Learning · Computer Science 2017-06-21 Justin Domke

In this paper, we introduce a novel family of iterative algorithms which carry out $\alpha$-divergence minimisation in a Variational Inference context. They do so by ensuring a systematic decrease at each step in the $\alpha$-divergence…

Computation · Statistics 2023-04-12 Kamélia Daudel , Randal Douc , François Roueff

Variational inference (VI) is widely used as an efficient alternative to Markov chain Monte Carlo. It posits a family of approximating distributions $q$ and finds the closest member to the exact posterior $p$. Closeness is usually measured…

Machine Learning · Statistics 2017-11-15 Adji B. Dieng , Dustin Tran , Rajesh Ranganath , John Paisley , David M. Blei

This work investigates the stability of (discrete) empirical interpolation for nonlinear model reduction and state field approximation from measurements. Empirical interpolation derives approximations from a few samples (measurements) via…

Numerical Analysis · Mathematics 2020-05-20 Benjamin Peherstorfer , Zlatko Drmač , Serkan Gugercin

Variational approaches to approximate Bayesian inference provide very efficient means of performing parameter estimation and model selection. Among these, so-called variational-Laplace or VL schemes rely on Gaussian approximations to…

Methodology · Statistics 2018-01-17 Jean Daunizeau

We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To…

Machine Learning · Statistics 2019-05-29 Francisco J. R. Ruiz , Michalis K. Titsias

The proliferation of computing devices has brought about an opportunity to deploy machine learning models on new problem domains using previously inaccessible data. Traditional algorithms for training such models often require data to be…

Two-sample inference for the difference of population means typically relies upon a Central Limit Theorem approximation. When data are drawn from a Negative Binomial distribution, previous work of Shilane et al. (2010) showed that a Normal…

Methodology · Statistics 2012-03-06 David Shilane , Derek Bean

In observational studies, the assumption of sufficient overlap (positivity) is fundamental for the identification and estimation of causal effects. Failing to account for this assumption yields inaccurate and potentially infeasible…

Methodology · Statistics 2025-04-07 Jaehyuk Jang , Suehyun Kim , Kwonsang Lee

We establish a novel convergent iteration framework for a weak approximation of general switching diffusion. The key theoretical basis of the proposed approach is a restriction of the maximum number of switching so as to untangle and…

Numerical Analysis · Mathematics 2023-07-06 Qinjing Qiu , Reiichiro Kawai

Variational Inference (VI) is a commonly used technique for approximate Bayesian inference and uncertainty estimation in deep learning models, yet it comes at a computational cost, as it doubles the number of trainable parameters to…

Machine Learning · Computer Science 2024-06-25 Christian Marius Lillelund , Martin Magris , Christian Fischer Pedersen

Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference. However, many ParVI approaches do not allow arbitrary…

Machine Learning · Computer Science 2021-08-12 Neale Ratzlaff , Qinxun Bai , Li Fuxin , Wei Xu

We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approximate posterior and the…

Machine Learning · Statistics 2019-03-19 Dmitry Molchanov , Valery Kharitonov , Artem Sobolev , Dmitry Vetrov

When methods of moments are used for identification of power spectral densities, a model is matched to estimated second order statistics such as, e.g., covariance estimates. If the estimates are good there is an infinite family of power…

Optimization and Control · Mathematics 2011-04-12 Per Enqvist