English
Related papers

Related papers: Importance Weighted Variational Inference without …

200 papers

Variational inference consists in finding the best approximation of a target distribution within a certain family, where `best' means (typically) smallest Kullback-Leiber divergence. We show that, when the approximation family is…

Computation · Statistics 2025-09-24 Yvann Le Fay , Nicolas Chopin , Simon Barthelmé

This paper investigates distributed zeroth-order optimization for smooth nonconvex problems, targeting the trade-off between convergence rate and sampling cost per zeroth-order gradient estimation in current algorithms that use either the…

Optimization and Control · Mathematics 2026-04-10 Huaiyi Mu , Yujie Tang , Jie Song , Zhongkui Li

Inference for models with recursively defined likelihoods is computationally demanding, limiting scalability to large datasets. We propose a stabilised weighted subsampling methodology for accelerated inference based on an unbiased…

Methodology · Statistics 2026-05-14 Matias Quiroz , Aishwarya Bhaskaran , Zixuan Wang , Thomas Goodwin

Variational Bayesian Monte Carlo (VBMC) is a recently introduced framework that uses Gaussian process surrogates to perform approximate Bayesian inference in models with black-box, non-cheap likelihoods. In this work, we extend VBMC to deal…

Machine Learning · Statistics 2020-10-20 Luigi Acerbi

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

Modern variational inference (VI) uses stochastic gradients to avoid intractable expectations, enabling large-scale probabilistic inference in complex models. VI posits a family of approximating distributions q and then finds the member of…

Machine Learning · Statistics 2021-02-24 Christian A. Naesseth , Fredrik Lindsten , David Blei

Importance sampling has become an indispensable strategy to speed up optimization algorithms for large-scale applications. Improved adaptive variants - using importance values defined by the complete gradient information which changes…

Machine Learning · Computer Science 2017-11-08 Sebastian U. Stich , Anant Raj , Martin Jaggi

The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been…

Machine Learning · Statistics 2019-02-28 Rui Shu , Hung H. Bui , Jay Whang , Stefano Ermon

This work introduces meta estimators that combine multiple multifidelity techniques based on control variates, importance sampling, and information reuse to yield a quasi-multiplicative amount of variance reduction. The proposed meta…

Computational Physics · Physics 2023-01-19 Frederick Law , Antoine Cerfon , Benjamin Peherstorfer , Florian Wechsung

Several algorithms involving the Variational R\'enyi (VR) bound have been proposed to minimize an alpha-divergence between a target posterior distribution and a variational distribution. Despite promising empirical results, those algorithms…

Machine Learning · Statistics 2023-07-20 Kamélia Daudel , Joe Benton , Yuyang Shi , Arnaud Doucet

In solving simulation-based stochastic root-finding or optimization problems that involve rare events, such as in extreme quantile estimation, running crude Monte Carlo can be prohibitively inefficient. To address this issue, importance…

Methodology · Statistics 2021-02-23 Shengyi He , Guangxin Jiang , Henry Lam , Michael C. Fu

Variational Inference (VI) offers a method for approximating intractable likelihoods. In neural VI, inference of approximate posteriors is commonly done using an encoder. Alternatively, encoderless VI offers a framework for learning…

Machine Learning · Computer Science 2023-01-18 Amir Zadeh , Santiago Benoit , Louis-Philippe Morency

As a computational alternative to Markov chain Monte Carlo approaches, variational inference (VI) is becoming more and more popular for approximating intractable posterior distributions in large-scale Bayesian models due to its comparable…

Machine Learning · Statistics 2023-06-05 Anirban Bhattacharya , Debdeep Pati , Yun Yang

We present a new Unbiased Minimal Variance (UMV) estimator for the purpose of reconstructing the large--scale structure of the universe from noisy, sparse and incomplete data. Similar to the Wiener Filter (WF), the UMV estimator is derived…

Astrophysics · Physics 2009-10-31 Saleem Zaroubi

Control variates are variance reduction tools for Monte Carlo estimators. They can provide significant variance reduction, but usually require a large number of samples, which can be prohibitive when sampling or evaluating the integrand is…

Methodology · Statistics 2023-06-08 Zhuo Sun , Alessandro Barp , François-Xavier Briol

We introduce data structures for solving robust regression through stochastic gradient descent (SGD) by sampling gradients with probability proportional to their norm, i.e., importance sampling. Although SGD is widely used for large scale…

Machine Learning · Computer Science 2022-07-19 Sepideh Mahabadi , David P. Woodruff , Samson Zhou

A simple and stable method for computing accurate expectation values of observable with Variational Monte Carlo (VMC) or Diffusion Monte Carlo (DMC) algorithms is presented. The basic idea consists in replacing the usual ``bare'' estimator…

Chemical Physics · Physics 2009-11-10 Roland Assaraf , Michel Caffarel

Estimating the gradients for binary variables is a task that arises frequently in various domains, such as training discrete latent variable models. What has been commonly used is a REINFORCE based Monte Carlo estimation method that uses…

Machine Learning · Computer Science 2021-06-01 Alek Dimitriev , Mingyuan Zhou

We propose a new framework of variance-reduced Hamiltonian Monte Carlo (HMC) methods for sampling from an $L$-smooth and $m$-strongly log-concave distribution, based on a unified formulation of biased and unbiased variance reduction…

Machine Learning · Computer Science 2021-02-10 Zhengmian Hu , Feihu Huang , Heng Huang

It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness of gradient-based optimisation methods such as stochastic…

Machine Learning · Computer Science 2024-02-21 Dominik Wagner , Basim Khajwal , C. -H. Luke Ong