Paper introduces f-divergence variational inference for broader application.
problem Variational inference limited to specific divergences.
method Generalizes variational inference to all f-divergences using f-divergence minimization.
result Unified framework for variational inference with arbitrary f-divergences.
Automates VI divergence selection for efficient few-shot learning.
problem Efficiently selecting divergence measures for VI to improve performance.
method Meta-learning algorithm to learn optimal divergence metric and variational parameter initialization.
result Meta-learning approach outperforms standard VI methods across various tasks.
A new VIS approach improves log-likelihood estimation in latent variable models.
problem Challenges in achieving high log-likelihood with VI for complex posterior distributions.
method Uses forward χ2 divergence to optimize proposal distribution for better log-likelihood estimation. result Consistently outperforms state-of-the-art baselines in log-likelihood and parameter estimation.
To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has been used for machine vision and medical applications, but VI can severely underestimates model uncertainty. Alpha-divergences are alternative …
DAIS minimizes symmetrized KL divergence between initial and target distributions.
problem Optimizing over initial distributions in importance sampling.
method Differentiable annealed importance sampling (DAIS) minimizing symmetrized KL divergence.
result DAIS minimizes symmetrized KL divergence between initial and target distributions.
We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a general framework for estimating the evidence lower bound (ELBO) in Variational Bayes. In this work, …
VI approximates complex densities faster than classical methods.
problem Approximating complex probability densities.
method Optimization of a family of probability density functions using KL divergence.
result VI converges faster than Markov Chain Monte Carlo.
A novel stepwise VI method using vine copulas for complex latent dependence.
problem Modeling complex latent dependence structures in probabilistic models.
method Stepwise estimation of vine copula parameters using Rényi divergence and a stopping criterion.
result Our method outperforms mean-field VI and is more parsimonious in complex applications.
New particle-based VI algorithm expands function class and improves scalability.
problem Limited function class in particle-based VI algorithms restricts flexibility and scalability.
method Introduces a functional regularization term to expand the function class and proposes PFG algorithm.
result Proposed PFG algorithm has larger function class, improved scalability, better adaptation to ill-conditioned distributions, and provable convergence.
VI struggles to fully quantify uncertainty when distributions don't factorize.
problem Uncertainty quantification in non-factorizable distributions.
method Analysis of variational inference trade-offs and divergence choices.
result Different divergences yield different measures of uncertainty in VI.
Develops possibilistic VI using maxitive Donsker-Varadhan formulation.
problem Adapting VI to possibilistic framework to handle uncertainty.
method Maxitive Donsker-Varadhan formulation for possibilistic VI.
result CBOpt optimizers achieve competitive performance in image classification.
New guarantees for VI in symmetric cases, extending previous results.
problem Symmetry in variational inference for complex distributions.
method Analysis of f-divergences and their stationary points under symmetry. result Symmetry-matching principles ensure recovery of mean and correlation matrix.
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 make inference tractable, we introduce the variational contrastive divergence (VCD)…
The paper improves guarantees for VI in symmetric cases.
problem Approximating intractable densities via VI with misspecified families.
method Extends previous robust VI results to wider divergences and non-log-concave targets.
result Guarantees for exact recovery of target mean and correlation matrix under various conditions.
This paper reviews recent advancements in amortized Variational Inference.
problem Scalability and efficiency issues in traditional Variational Inference.
method Systematic review of various Variational Inference techniques, focusing on amortized approaches.
result Amortized Variational Inference improves scalability and efficiency for generative modeling tasks.
Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models. These models are usually intractable and thus require approximate inference. Variational inference (VI) lets us approximate a high-dimensional Bayesian posterior with a simpler variational distribution by solv…
A new method interpolates between sampling and variational inference using stochastic mixtures.
problem Combining the strengths of sampling and variational inference methods.
method Develops a framework using stochastic mixtures of simple component distributions to interpolate between sampling and variational inference.
result Improves on both sampling and variational inference methods by reducing bias and variance.
Enhanced DeepONet framework with uncertainty quantification for complex operators.
problem Learning complex operators with uncertainty quantification.
method Generalised variational inference (GVI) using Rényi's α-divergence.
result Superior predictive accuracy and uncertainty quantification.
Develops variational inference for Neyman-Scott processes for faster sampling.
problem Slow mixing time in MCMC for posterior sampling in Neyman-Scott processes.
method Variational inference algorithm for Neyman-Scott processes, minimizing KL divergence.
result Achieves better prediction performance than MCMC with limited computational time.
Recent work in variational inference (VI) uses ideas from Monte Carlo estimation to tighten the lower bounds on the log-likelihood that are used as objectives. However, there is no systematic understanding of how optimizing different objectives relates to approximating the posterior distribution. Developing such a conn…
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 via a divergence D(q∣∣p) from q to p. While successful, this approach al…
Paper addresses variational inference issues in Bayesian neural networks.
problem Negative infinite ELBO for function-space priors in BNNs.
method Regularized KL divergence for well-defined function-space variational inference.
result Method provides competitive uncertainty estimates for BNNs.
One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this paper, we review variational inference (V…
The paper examines VI for overparameterized BNNs, revealing a trade-off between likelihood and KL terms.
problem Critical issue in mean-field VI training for overparameterized BNNs.
method Theoretical and empirical study of overparameterized two-layer BNNs using VI.
result A trade-off between likelihood and KL terms in overparameterized regime, with KL scaling crucial.
A new method combines VI and IS to improve Bayesian inference accuracy.
problem Bayesian inference often underestimates posterior tails, leading to miscalibration and degeneracy.
method Proposes a novel combination of optimization and sampling techniques using the forward KL divergence.
result The method guarantees asymptotic consistency and fast convergence to optimal IS and variational approximations.
Geometric analysis improves convergence of variational inference.
problem Challenges in analyzing convergence of variational inference due to non-convexity and non-smoothness.
method Exploits exponential family structure and Bregman divergences to geometrically analyze the optimization landscape.
result Establishes non-asymptotic convergence rates for gradient descent algorithms.
A new EVI framework improves ParVI methods by maintaining variational structure and reducing KL-divergence.
problem Improving variational inference methods for better approximation of target distributions.
method EVI framework that minimizes the VI objective function based on an energy-dissipation law, including a new 'Approximation-then-Variation' scheme.
result The new scheme significantly decreases KL-divergence and outperforms existing ParVI methods in fidelity.
Unified framework for efficient trans-dimensional Bayesian inference using VI and NFs.
problem Efficient trans-dimensional Bayesian inference with reduced computational cost.
method Variational inference with normalizing flows to train transport proposals.
result Our approach minimizes reverse KL divergence and reduces computational cost.
Paper analyzes VI for location-scale families, proving robustness guarantees for mean and correlation recovery.
problem Misspecification in VI for intractable target densities.
method Variational inference on location-scale families with symmetries.
result VI recovers mean and correlation matrix under specific symmetries.
New method guarantees global convergence in variational inference.
problem Limited convergence to local optima in variational inference.
method Minimizes inclusive KL divergence using neural networks and neural tangent kernel.
result Gradient descent dynamics converge to a unique solution in function space.
This paper compares gradient estimators in importance-weighted VI and justifies the superiority of DREP over REP.
problem Understanding the impact of gradient estimators on importance-weighted VI algorithms.
method Unified theoretical comparison of reparameterized and doubly-reparameterized gradient estimators tied to IWAE, VR, and VR-IWAE bounds.
result Formally justifies the superiority of doubly-reparameterized gradient estimators over reparameterized ones in importance-weighted VI.
CAVI converges globally or locally exponentially for two-block models.
problem Convergence analysis of coordinate ascent variational inference (CAVI).
method Analysis of CAVI convergence using functional analysis and optimization.
result General conditions for certifying global or local exponential convergence of CAVI.
We formalize the problem of learning interdomain correspondences in the absence of paired data as Bayesian inference in a latent variable model (LVM), where one seeks the underlying hidden representations of entities from one domain as entities from the other domain. First, we introduce implicit latent variable models,…
The paper tackles approximate unlearning from a subset of training data using variational inference.
problem Unlearning from a small subset of erased training data while maintaining the posterior belief from the full data.
method Formulates unlearning as minimizing KL divergence, equivalent to minimizing an evidence upper bound. Uses variational inference to approximate posterior beliefs and proposes two tricks to handle challenges.
result Demonstrates the effectiveness of the proposed unlearning methods on various Bayesian models.
This study analyzes theoretical guarantees for VI with fixed-variance Gaussian mixtures.
problem Theoretical analysis of variational inference with non-Gaussian distributions.
method Formulates variational inference as minimizing a mollified relative entropy, solving it through gradient descent on particle positions.
result Establishes descent lemma and approximation error bounds for optimization of variational inference.
Statistical inference of analytically non-tractable posteriors is a difficult problem because of marginalization of correlated variables and stochastic methods such as MCMC and VI are commonly used. We argue that stochastic KL divergence minimization used by MCMC and VI is noisy, and we propose instead EL_2O, expectati…
The paper analyzes Bayesian neural networks trained with VI, proving a law of large numbers for different schemes.
problem Training Bayesian neural networks with variational inference.
method Analyzes three training schemes: exact estimation, Bayes by Backprop, and Minimal VI.
result All training schemes converge to the same mean-field limit.
A new upper bound for variational inference improves the efficiency of Bayesian deep learning.
problem Improving variational inference in Bayesian deep learning.
method Presented a new upper bound (EUBO) for evidence, derived from KL-divergence and log marginal likelihood, and used SGD for optimization.
result The new upper bound (EUBO) is tighter than previous methods and outperforms state-of-the-art results in Bayesian neural networks.
BF-VI improves posterior approximation in complex models.
problem Inefficient posterior approximations in complex models.
method Combines normalizing flows and Bernstein polynomial transformations.
result BF-VI outperforms other VI methods in approximating complex multivariate posteriors.
New methods minimize GFlowNet training divergences for better sampling.
problem Training GFlowNets with KL divergence leads to biased and high-variance estimators.
method Design and implement efficient estimators for four divergence measures.
result Properly minimizing these divergences yields a provably correct and effective training scheme.
Stein variational gradient descent improves inference in Gaussian process models.
problem Inference in Gaussian process models with non-Gaussian likelihoods and large data volumes is computationally intensive and inaccurate with traditional methods.
method Stein variational gradient descent (SVGD) for non-parametric inference.
result SVGD monotonically decreases the Kullback-Leibler divergence from the sampling distribution to the true posterior.
RVI accelerates encoderless VI for faster convergence.
problem Slow convergence in encoderless VI methods.
method Introduces Relay Variational Inference (RVI) for faster learning.
result RVI outperforms existing methods in convergence speed and performance.
A-VI can approximate F-VI under certain conditions, improving inference in some models.
problem Approximate Bayesian inference using factorized distributions.
method Amortized variational inference (A-VI) learns a common inference function for latent variables.
result A-VI can close the amortization gap in simple hierarchical models.
We develop a parallel variational inference (VI) procedure for use in data-distributed settings, where each machine only has access to a subset of data and runs VI independently, without communicating with other machines. This type of "embarrassingly parallel" procedure has recently been developed for MCMC inference al…
A new variational inference method using Gaussian score matching.
problem Approximating posterior distributions in Bayesian statistics.
method Score matching principle applied to variational inference.
result Gaussian score matching VI (GSM-VI) is faster and requires fewer gradient evaluations.
New findings on Malgrange-Galois groupoid for Painlevé VI equation parameters.
problem Understanding transformations preserving specific forms for Painlevé VI equation.
method Computed Malgrange-Galois groupoid for Painlevé VI family with all parameters.
result Solutions of Painlevé VI do not satisfy new partial differential equations.
We advocate an optimization-centric view on and introduce a novel generalization of Bayesian inference. Our inspiration is the representation of Bayes' rule as infinite-dimensional optimization problem (Csiszar, 1975; Donsker and Varadhan; 1975, Zellner; 1988). First, we use it to prove an optimality result of standard…
Novel approach simplifies VI problems with faster performance.
problem Black-box VI optimization problems.
method Sample Average Approximation (SAA) combined with quasi-Newton methods and line search.
result Achieves faster performance than existing methods.