Natural-gradient methods improve Bayesian inference in complex models.
problem Computational challenges in Bayesian inference for complex models.
method Derive fast natural-gradient updates for variational inference.
result Natural-gradient methods provide more accurate local approximations.
Efficient variational inference for probabilistic models using importance sampling.
problem Efficiently approximating posterior distributions in probabilistic models.
method Develops importance sampled stochastic gradient descent for variational inference.
result Importance sampled stochastic gradient descent outperforms standard methods for various models.
A new natural gradient accounts for correlated variational parameters in variational inference.
problem Traditional natural gradients fail to correct for correlations in variational inference.
method Construct a new natural gradient called the Variational Predictive Natural Gradient (VPNG).
result VPNG accounts for the relationship between model parameters and variational parameters.
Square-root natural-gradient improves variational inference convergence.
problem Challenges in establishing theoretical convergence guarantees for natural-gradient descent.
method Square-root parameterization for Gaussian covariance.
result Establishes novel convergence guarantees for natural-gradient Gaussian inference.
New method uses variational inference for better reinforcement learning policies.
problem Improving policy gradient methods in reinforcement learning.
method Explicitly minimizing KL divergence to match target distribution for Bayesian parameterization.
result Enhanced performance in TRPO, PPO, and Bayesian Neural Network reinforcement learning.
We extend natural-gradient methods to mixtures of exponential-family distributions, improving inference speed.
problem Complex, multimodal posterior distributions are difficult to approximate with simple exponential-family distributions.
method We use minimal conditional-EF representations and derive simple natural-gradient updates.
result Our natural-gradient method converges faster than black-box methods with reparameterization gradients.
Paper analyzes inclusive KL inference using Wasserstein gradient flows.
problem Analyzing inclusive KL inference with mathematical tools.
method Gradient flows derived from PDE analysis.
result Unified view of existing sampling algorithms as inclusive-KL inference.
This paper shows equivalence between SVGD and BBVI using kernel gradient flows.
problem Bayesian inference methods and their equivalence.
method Formalizes equivalence between SVGD and BBVI using kernel gradient flows.
result BBVI corresponds precisely to SVGD when using the neural tangent kernel.
SVIGL speeds up convergence in stochastic variational inference.
problem Optimizing log-posterior in random field models is difficult.
method Stochastic variational inference with gradient linearization.
result SVIGL improves convergence speed with comparable KL divergence.
This paper bridges variational inference and Wasserstein gradient flows.
problem Combining variational inference and Wasserstein gradient flows for more efficient approximations.
method Recasting Bures-Wasserstein gradient flow as a Euclidean gradient flow and using path-derivative gradient estimator.
result A new gradient estimator for f-divergences that can be implemented using machine learning libraries. A new method for approximate inference using Wasserstein gradient flows.
problem Approximate inference for diffusion processes.
method Discretization-free inference method based on Wasserstein gradient flow.
result Performance comparable to state-of-the-art for nonlinear filtering tasks.
NVGD uses neural networks to infer distributions without kernel choices.
problem Challenges in choosing kernel functions for SVGD.
method NVGD parameterizes the witness function of the Stein discrepancy with a neural network.
result NVGD achieves good performance on various inference problems.
A new method for efficient inference in probabilistic programs with mixed support.
problem Challenges in inference for programs with both continuous and discrete latent variables.
method Stochastic gradient Markov Chain Monte Carlo algorithms.
result Outperforms existing composing inference baselines and works almost as well as inference in marginalized versions.
Review of gradient-based algorithms in statistical inference problems.
problem Understanding the dynamics of gradient-based algorithms in statistical inference.
method Insights from physics of glassy systems.
result Quantitative and qualitative understanding of algorithm performance.
Unified framework for statistical inference in gradient boosting regression.
problem Challenges in statistical inference and uncertainty quantification for gradient boosting.
method Integrates dropout or parallel training with regularization for CLT in boosting.
result Increasing dropout rate and parallel trees enhances signal recovery and performance.
Paper provides variance bounds for variational inference.
problem Understanding the variance of stochastic gradient estimators in variational inference.
method Analyzes reparameterization estimators under smoothness and location-scale assumptions.
result Gives provable bounds on gradient variance, showing they are optimal under stated conditions.
A new ParVI framework improves particle-based variational inference methods.
problem Non-trivial kernel design in particle-based variational inference methods.
method Proposes a generalized Wasserstein gradient descent (GWG) framework with broader regularizers.
result Demonstrates strong convergence guarantees and effectiveness on simulated and real data.
This work improves variational inference by reducing gradient variance.
problem Hard optimization of flexible variational distributions.
method Control variate based on quadratic approximation of the model's mean and covariance.
result Significant improvement in gradient variance and optimization convergence.
This work proposes a new method for variational inference using Wasserstein gradient descent.
problem Optimizing variational parameters to match a true posterior distribution.
method Reinterpreting VI as an optimization problem over a variational parameter space, using Wasserstein gradient descent.
result The proposed Wasserstein gradient descent can be seen as a generalization of existing optimization techniques in VI.
Improves PSR learning by refining spectral initialization with PSIM-style updates.
problem Inference performance of PSRs is poor despite good theoretical guarantees.
method Combines spectral algorithms for PSRs with PSIM-style updates for inference-based loss optimization.
result Inference Gradients outperforms PSRs and PSIMs on real and synthetic data.
New method reduces inference variance for faster optimization.
problem High variance in black-box variational inference.
method Joint control variate addressing both data subsampling and Monte Carlo noise.
result Significantly reduced gradient variance, leading to faster optimization.
Unified framework analyzes privacy risks from gradients in distributed learning.
problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.
Proposes a new algorithm for efficient probabilistic inference.
problem Efficient probabilistic inference in deep models with graphical structures.
method Structured inference networks and variational message-passing algorithm.
result Enables fast and efficient natural-gradient inference for deep structured models.
Improves understanding of stochastic NGVI convergence rates.
problem Lack of knowledge about non-asymptotic convergence rates in stochastic NGVI.
method Proved non-asymptotic convergence rates for conjugate likelihoods and showed implicit optimization for non-conjugate likelihoods.
result First O(T1) non-asymptotic convergence rate for stochastic NGVI in conjugate likelihoods. Enhances SVGD with matrix-valued kernels for faster inference.
problem Efficient approximate inference in complex probability landscapes.
method Integrates geometric information through matrix-valued kernels in SVGD.
result Significant improvement in real-world Bayesian inference tasks.
Simplifies gradient estimation for variational inference with reduced variance.
problem Reducing variance in gradient estimation for variational inference.
method Proposes a new gradient estimator by removing the score function term from the reparameterized gradient.
result The new estimator has zero variance as the approximate posterior approaches the exact posterior.
New method scales Bayesian inference for nonlinear SSMs using buffered stochastic gradient.
problem Inference for nonlinear, non-Gaussian SSMs is computationally challenging and particle degeneracy increases with longer series.
method Extends stochastic gradient MCMC to nonlinear SSMs using particle methods and error bounds.
result Demonstrates the importance of particle buffered stochastic gradient for long sequential data.
Enhances optimization and sampling methods using ensemble-based gradient inference.
problem Improving ensemble-based methods for optimization and sampling.
method Ensemble-based gradient inference (EGI) to extract higher-order derivatives from particle ensembles.
result Augmented algorithms outperform gradient-free variants, especially in multimodal and non-Gaussian settings.
The paper develops statistical inference for gradient flows in optimization.
problem Uncertainty quantification along the entire optimization path.
method Uniform central limit theorem and algorithm-aware covariance estimator.
result Asymptotically valid confidence intervals for target parameter.
PE-SVI reduces SVI inference complexity by finding a suitable start point.
problem Complex posterior inference in graphical models leads to suboptimal learning.
method PE-SVI uses a pseudo-encoded start point to reduce gradient steps and step sizes.
result PE-SVI achieves the same ELBo objective as SVI with less than 1% of the required steps.
GeoPhy uses geometric gradients to efficiently infer phylogenetic trees from molecular data.
problem Challenges in accurately inferring species relationships from molecular data due to combinatorially vast tree topologies.
method Introduces a novel, fully differentiable formulation of phylogenetic inference using geometric spaces and variational Bayesian methods.
result Significantly outperforms other approximate Bayesian methods in inferring phylogenetic trees.
RSVGD improves SVGD for Bayesian inference on Riemannian manifolds.
problem Bayesian inference on Riemannian manifolds.
method Develops RSVGD, a generalization of SVGD to Riemann manifolds.
result Advantages over SVGD in exploring distribution geometry and particle-efficiency.
Gradient-free SVGD improves inference for complex distributions.
problem Applying SVGD when gradients are unavailable.
method GF-SVGD, using a surrogate gradient and re-weighting.
result GF-SVGD outperforms gradient-free MCMC methods.
This work proposes new methods for variational inference using gradient flows on Gaussian measures.
problem Developing algorithmic guarantees for variational inference.
method Proposes principled methods for variational inference using gradient flows on the Bures--Wasserstein space of Gaussian measures.
result Strong theoretical guarantees for log-concave posteriors.
VIND reduces gradient variance for non-Gaussian approximations.
problem Improving Variational Inference for non-Gaussian distributions.
method Extends reparameterization trick to exponential families using numerical derivatives and tight coupling.
result Reduces gradient variance, leading to better posterior approximations.
This work proposes using zero-variance control variates to reduce variance in pathwise gradient estimators for variational inference.
problem Pathwise gradient estimators in variational inference have high variance, leading to inefficient optimization.
method Apply zero-variance control variates to pathwise gradient estimators.
result Zero-variance control variates can significantly reduce the variance of pathwise gradient estimators without requiring complex assumptions.
Paper improves variational inference convergence using many control variates.
problem High variance in gradient estimates hinders variational inference convergence.
method Develops a Bayesian risk minimization framework to combine many control variates.
result Combining many control variates significantly improves inference convergence.
VarGrad reduces variance in ELBO gradient estimation for variational inference.
problem Improving the variance of gradient estimators in variational inference.
method VarGrad uses a new log-variance loss to estimate the ELBO gradient, achieving lower variance than the score function method.
result VarGrad offers a lower variance gradient estimator compared to other methods.
New method speeds up inference for dynamical systems with sparse data.
problem Challenges in applying gradient matching methods to real-world, partially observable systems.
method Scalable variational inference framework for ordinary differential equations.
result Offers computational speedups, improved accuracy, and works well under model misspecifications.
U-statistics improve gradient estimation in importance-weighted variational inference.
problem High variance in gradient estimation for importance-weighted variational inference.
method Use U-statistics to average base gradient estimators on overlapping batches of size m, achieving lower variance.
result U-statistic variance reduction leads to modest to significant improvements in inference performance.
A new ML-based framework improves variational inference efficiency.
problem Efficient and accurate gradient estimation in variational inference.
method Multilevel Monte Carlo (MLMC) with reparameterized gradient estimators and adaptive learning rate.
result Our method achieves faster convergence and reduces gradient variance.
Quantized Variational Inference improves ELBO optimization with fast convergence.
problem Maximizing Evidence Lower Bound (ELBO) for variational inference.
method Optimal Voronoi Tesselation for variance-free gradients, Richardson extrapolation for asymptotic improvement.
result Quantized Variational Inference leads to fast convergence with comparable computational cost.
SING improves state inference in latent SDE models for better drift function estimation.
problem Intractable posterior inference in latent SDE models.
method Natural gradient variational inference.
result SING provides faster and more reliable inference in latent SDE models.
A method for efficient approximate inference on discrete distributions.
problem Applying SVGD to discrete distributions.
method Transforming discrete distributions to piecewise continuous distributions for SVGD application.
result Outperforms traditional algorithms and ensemble methods on discrete graphical models.
New framework improves variational inference with Markov chain methods.
problem Challenges of minimizing KL divergence with stochastic gradient descent.
method Markov chain score ascent (MCSA) methods, including parallel MCSA (pMCSA).
result Improved theoretical and empirical performance of MCSA methods.
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.
New guarantees for black-box variational inference methods.
problem Insufficient theoretical guarantees for black-box variational inference.
method Novel convergence guarantees for stochastic optimization of variational inference.
result Provable convergence of proximal and projected stochastic gradient descent for variational inference.
Improved Hamiltonian Monte Carlo for Bayesian inference reduces variance and improves performance.
problem Efficiently sampling from posterior distributions in Bayesian inference with stochastic gradients.
method Variance reduction techniques applied to Hamiltonian Monte Carlo.
result Theoretical and experimental improvements in convergence and performance compared to variance-reduced Langevin dynamics.