New algorithm optimizes variational objective for marginal inference.
problem Optimizing the tree-reweighted variational objective over the marginal polytope.
method Barrier Frank-Wolfe algorithm based on conditional gradient method, leveraging MAP solvers.
result More accurate results than TRW algorithms that optimize over local consistency relaxation.
Graphical models trained using maximum likelihood are a common tool for probabilistic inference of marginal distributions. However, this approach suffers difficulties when either the inference process or the model is approximate. In this paper, the inference process is first defined to be the minimization of a convex f…
New method improves variational inference for likelihood-free models.
problem Efficiently approximate posterior distributions in likelihood-free models.
method Forward amortized inference using joint-contrastive variational loss.
result Forward amortized inference optimizes exact posterior marginals in mean-field approximations.
New method improves MAP inference efficiency and reliability.
problem Efficient inference in systems with latent variables or missing data.
method Generalized dual decomposition on a convex decomposition bound.
result Framework converges monotonically and is faster/reliable than previous methods.
Efficiently estimates marginal posteriors for complex simulations.
problem Bayesian inference in high-dimensional, intractable likelihood scenarios.
method Simulates and estimates low-dimensional marginal posteriors, using truncated indicators.
result Simulator efficiency and robustness testing of inference results.
We develop an HMC algorithm to easily marginalize random effects in LMMs.
problem Bayesian inference in LMMs is challenging, especially marginalizing random effects.
method Developed an HMC algorithm to marginalize random effects in LMMs efficiently.
result Marginalization is always beneficial when applicable and improves various models, especially cognitive science models.
Estimates high-dimensional posterior densities by marginal distributions and neural networks.
problem High-dimensional probability density estimation for inference is difficult.
method Direct estimation of lower-dimensional marginal distributions, using Moment Networks for fast computation of moments.
result Demonstrates estimation of gravitational wave time series and applications in cosmology.
We present a max-margin nonparametric latent feature model, which unites the ideas of max-margin learning and Bayesian nonparametrics to discover discriminative latent features for link prediction and automatically infer the unknown latent social dimension. By minimizing a hinge-loss using the linear expectation operat…
Max-margin method for nonparametric latent feature models improves link prediction.
problem Link prediction in statistical networks.
method Max-margin learning combined with Bayesian nonparametrics.
result Improved link prediction accuracy on large-scale networks.
A new algorithm estimates aggregate marginals from noisy data in an online manner.
problem Estimating aggregate marginals of a Markov chain from noisy aggregate observations.
method Sliding window Sinkhorn belief propagation (SW-SBP) algorithm.
result Demonstrated improved performance on inferring population flow.
Improves hyperparameter learning in GP models with non-conjugate likelihoods.
problem Hyperparameter learning entangled with approximate inference in GP models.
method Hybrid training procedure combining VI for inference and EP-like marginal likelihood approximation for hyperparameter learning.
result Empirically demonstrates the effectiveness of the proposed training procedure across various data sets.
Graphical models use graphs to compactly capture stochastic dependencies amongst a collection of random variables. Inference over graphical models corresponds to finding marginal probability distributions given joint probability distributions. In general, this is computationally intractable, which has led to a quest fo…
Variational Prediction simplifies Bayesian inference without test time costs.
problem Bayesian inference's computational costs and posterior predictive distribution marginalization.
method Variational Prediction learns a variational approximation to the posterior predictive distribution using a variational bound.
result Directly learns a variational approximation to the posterior predictive distribution without test time marginalization costs.
MSBM extends SB for multi-marginal trajectory inference.
problem Trajectory inference from multiple discrete snapshots.
method Multi-Marginal Schrödinger Bridge Matching (MSBM) using iterative Markovian fitting (IMF).
result MSBM effectively captures complex trajectories and respects intermediate distributions.
Efficient algorithm for Bayesian networks reduces marginal probability distribution computation.
problem Exact computation of marginal probability distribution is NP-hard for categorical variables in Bayesian networks.
method Divide-and-conquer approach exploiting graphical properties of Bayesian networks.
result Novel algorithm outperforms state-of-the-art methods in classification and cancer subtype identification.
Improved particle Gibbs sampling by marginalizing parameters.
problem Bayesian inference in high-dimensional state-space models is challenging.
method Marginalized particle Gibbs sampling, combining MCMC and sequential Monte Carlo.
result Marginalization improves performance beyond the Gibbs sampler, scaling linearly.
Bayesian framework improves uncertainty quantification in Gaussian process models.
problem High correlations between latent variables and hyperparameters in Gaussian process models.
method Uses pseudo-marginal method to estimate marginal likelihood and explore posterior of hyperparameters.
result Demonstrates improved uncertainty quantification and multimodality in hyperparameters compared to variational inference.
Deep Gaussian processes provide a flexible approach to probabilistic modelling of data using either supervised or unsupervised learning. For tractable inference approximations to the marginal likelihood of the model must be made. The original approach to approximate inference in these models used variational compressio…
Improved MUSE boosts performance and reduces error in Bayesian inference.
problem Hierarchical Bayesian inference problems
method Implicit differentiation applied to MUSE algorithm
result Significant speedup and improved accuracy compared to Hamiltonian Monte Carlo
Belief Propagation has been widely used for marginal inference, however it is slow on problems with large-domain variables and high-order factors. Previous work provides useful approximations to facilitate inference on such models, but lacks important anytime properties such as: 1) providing accurate and consistent mar…
Bayesian inference for wide neural networks using Edgeworth expansion.
problem Analyzing the non-Gaussian behavior of wide neural networks in Bayesian inference.
method Proposed a non-Gaussian distribution using multivariate Edgeworth expansion for finite-width neural networks.
result Derived non-Gaussian posterior distribution in Bayesian regression tasks.
UM trains a neural network to approximate marginal distributions in probabilistic programs.
problem High computational cost and lack of theoretical guarantees in inference methods for probabilistic programs.
method Combining samples from a probabilistic program prior with an augmentation method to train a neural network for any conditional marginal distribution.
result UM trains a single neural network to approximate any conditional marginal distribution, amortizing inference costs.
Kernel methods have revolutionized the fields of pattern recognition and machine learning. Their success, however, critically depends on the choice of kernel parameters. Using Gaussian process (GP) classification as a working example, this paper focuses on Bayesian inference of covariance (kernel) parameters using Mark…
This paper identifies and bounds ICE central moments using PO marginal central moments.
problem Identifying and characterizing treatment effect heterogeneity.
method Using only marginal central moments of potential outcomes, the paper identifies and bounds central moments of individual causal effects.
result Identification and bounding of central moments of ICE using marginal moments of POs.
Max-margin deep generative models improve predictive performance in supervised and semi-supervised learning.
problem Insufficient discriminative ability of deep generative models in making accurate predictions.
method Introduce max-margin principle to improve discriminative learning while retaining generative capability.
result Significant improvement in prediction performance with max-margin learning.
Improved likelihood-free inference by localizing and refining low-dimensional approximations.
problem Poor performance of common likelihood-free methods in high-dimensional models.
method Localisation followed by refinement of low-dimensional summaries.
result Improved accuracy in marginal posteriors through localized and refined approximations.
New insights into using IPF for inferring dynamic networks from marginals.
problem Inferring dynamic networks from time-aggregated adjacency matrices and time-varying marginals.
method Identifying a generative network model and establishing its maximum likelihood estimates via IPF, with convergence guarantees for sparse data.
result IPF provides principled estimation of dynamic networks from marginals under certain conditions, with structure-dependent error bounds and guaranteed convergence for sparse data.
A new variational method for SSMs improves inference efficiency.
problem Hard variational inference for state space models.
method Proposes variational marginal particle filter (VMPF) based on Rao-Blackwellization.
result VMPF provides tighter variational bounds and sometimes benefits from unbiased reparameterization.
Corrects errors in ILA for Bayesian inference in LGMs.
problem Error in ILA for non-Gaussian likelihoods in LGMs.
method Importance sampling scheme to correct ILA errors.
result Corrected posterior converges to the true posterior with increased samples.
We improve DGP models by using importance-weighted variational inference for better accuracy.
problem Accurate modeling of non-Gaussian marginals in deep Gaussian processes.
method Introduced noisy latent covariates and an importance-weighted objective for variational inference.
result The importance-weighted objective consistently outperforms classical variational inference, especially for deeper models.
Frugal Flows learn complex data and infer marginal causal effects.
problem Challenges in estimating marginal causal effects from complex data.
method Frugal Flows use normalizing flows to flexibly learn data and infer causal quantities.
result Frugal Flows can generate synthetic data that closely matches real-world data and exactly parameterize causal quantities.
Learn invariances in models using the marginal likelihood.
problem Generalizing well in supervised learning tasks.
method Learn invariances in model structure using the marginal likelihood.
result Demonstrated for Gaussian process models, reducing complexity of invariant models.
Pseudo-Marginal HMC combines HMC and pseudo-marginal MH for better posterior sampling.
problem Intractable likelihood in Bayesian inference makes sampling difficult.
method Combines HMC and pseudo-marginal MH approaches, controlled by a precision parameter N.
result Pseudo-marginal HMC outperforms standard HMC and pseudo-marginal MH in high-dimensional scenarios.
New algorithm for efficient inference over tree-structured graphs.
problem Inference over probabilistic graphical models with aggregate data.
method Optimal transport theory, Sinkhorn/iterative scaling algorithm, belief propagation.
result Global convergence and polynomial computational complexity.
This work introduces a noise-adaptive conformal inference method for better prediction sets in noisy data.
problem Real-world complications like random label noise limit the effectiveness of conformal inference.
method An adaptive conformal inference method capable of handling deviations from exchangeability.
result Informative prediction sets with tight marginal coverage guarantees in noisy data.
New method identifies drift and diffusivity from SDE marginals.
problem Challenging task to identify drift and diffusion from SDE population dynamics.
method Proposes nn-APPEX, a Schrodinger Bridge-based inference method.
result Gradient-flow drift and Brownian diffusivity jointly identifiable from marginals.
New method calibrates deep neural network predictions for better uncertainty quantification.
problem Uncertainty quantification for deep neural network predictions.
method Conditional Gaussian prior, copula process, non-parametric marginal distribution.
result Marginally-calibrated predictions from distributional DNN regression.
We speed up marginal inference by ignoring factors that do not significantly contribute to overall accuracy. In order to pick a suitable subset of factors to ignore, we propose three schemes: minimizing the number of model factors under a bound on the KL divergence between pruned and full models; minimizing the KL dive…
DMVI uses diffusion models for efficient probabilistic inference in PPLs.
problem Efficient probabilistic inference in complex probabilistic programming languages.
method DMVI employs diffusion models as variational approximations to the posterior distribution, optimizing a bound on the marginal likelihood.
result DMVI produces more accurate posterior inferences than existing methods in PPLs with similar computational cost and less manual tuning.
Improved variational inference by enforcing consistency with linear response.
problem Inconsistent variational approximations in inference methods.
method Introducing constraints on covariance to ensure consistency with linear response.
result Improvement in marginal probability distribution inference.
We extend probabilistic programming to handle conditioning on marginal distributions.
problem Conditioning probabilistic programs on marginal distributions of observable variables.
method We define and implement stochastic conditioning, allowing inference in probabilistic programs conditioned on marginal distributions.
result We demonstrate the effectiveness of stochastic conditioning in various real-life scenarios.
Combines VI and EP for better Gaussian process hyperparameter learning.
problem Improving hyperparameter learning in Gaussian processes for better performance.
method Hybrid training procedure combining Variational Inference (VI) for posterior inference and Expectation Propagation (EP) for hyperparameter learning.
result The hybrid training procedure provides a better learning objective and generalizes better than using only VI or EP.
Localized inference for large graphs with error bounds.
problem Efficiently answering queries in large graphical models.
method Localized algorithm with error bounds based on Dobrushin's theorem.
result Localized inference provides fast and accurate approximations for large models.
New algorithm improves solving constraint satisfaction problems by avoiding contradictory estimates.
problem Improving solving efficiency for constraint satisfaction problems with approximate marginals.
method Introducing a streamlined branching strategy based on streamlining constraints.
result Streamlined solvers outperform decimation-based solvers on random k-SAT instances, reducing the gap in performance by 16.3% on average.
SparseMAP selects sparse structures efficiently for structured prediction.
problem Efficiently searching over combinatorial structures in structured prediction.
method SparseMAP: a new method for sparse structured inference with a differentiable loss function.
result SparseMAP selects only a few global structures efficiently.
Paper introduces md-vtrees for efficient probabilistic and causal inference.
problem Efficient inference in complex probabilistic models.
method Introduces md-vtrees to generalize tractability conditions for advanced inference queries.
result Derives first polytime algorithms for causal inference queries.
New methods improve Bayesian inference and decision-making in online learning.
problem Current Bayesian deep learning does not fully utilize joint predictives for sequential decision-making.
method Proposes new evaluation settings for active learning and active sampling, focusing on marginal and joint cross-entropies.
result Initial experiments suggest challenges in applying current BDL inference techniques in high-dimensional spaces.
A new neural network approximates conditional distributions in generative models.
problem Inference in generative models with varying observation sets.
method Combining samples with a masking function and a neural network for amortized inference.
result Single neural network approximates all conditional marginal distributions efficiently.