An Equivalence between Bayesian Priors and Penalties in Variational Inference

• URL: http://arxiv.org/abs/2002.00178v3
• Date: Wed, 7 Feb 2024 13:17:55 GMT
• Title: An Equivalence between Bayesian Priors and Penalties in Variational Inference
• Authors: Pierre Wolinski, Guillaume Charpiat, Yann Ollivier
• Abstract summary: In machine learning, it is common to optimize the parameters of a probabilistic model, modulated by an ad hoc regularization term that penalizes some values of the parameters. We fully characterize the regularizers that can arise according to this procedure, and provide a systematic way to compute the prior corresponding to a given penalty.
• Score: 8.45602005745865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In machine learning, it is common to optimize the parameters of a probabilistic model, modulated by an ad hoc regularization term that penalizes some values of the parameters. Regularization terms appear naturally in Variational Inference, a tractable way to approximate Bayesian posteriors: the loss to optimize contains a Kullback--Leibler divergence term between the approximate posterior and a Bayesian prior. We fully characterize the regularizers that can arise according to this procedure, and provide a systematic way to compute the prior corresponding to a given penalty. Such a characterization can be used to discover constraints over the penalty function, so that the overall procedure remains Bayesian.

Related papers

• Reparameterization invariance in approximate Bayesian inference [32.88960624085645]
  We develop a new geometric view of reparametrizations from which we explain the success of linearization. We demonstrate that these re parameterization invariance properties can be extended to the original neural network predictive.
  arXiv  Detail & Related papers  (2024-06-05T14:49:15Z)
• Generalized Laplace Approximation [23.185126261153236]
  We introduce a unified theoretical framework to attribute Bayesian inconsistency to model misspecification and inadequate priors. We propose the generalized Laplace approximation, which involves a simple adjustment to the Hessian matrix of the regularized loss function. We assess the performance and properties of the generalized Laplace approximation on state-of-the-art neural networks and real-world datasets.
  arXiv  Detail & Related papers  (2024-05-22T11:11:42Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability [50.44439018155837]
  We propose to include a calibration term directly into the training objective of the neural model. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
  arXiv  Detail & Related papers  (2023-10-20T10:20:45Z)
• Variational Prediction [95.00085314353436]
  We present a technique for learning a variational approximation to the posterior predictive distribution using a variational bound. This approach can provide good predictive distributions without test time marginalization costs.
  arXiv  Detail & Related papers  (2023-07-14T18:19:31Z)
• Bayesian Renormalization [68.8204255655161]
  We present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference. The main insight of Bayesian Renormalization is that the Fisher metric defines a correlation length that plays the role of an emergent RG scale. We provide insight into how the Bayesian Renormalization scheme relates to existing methods for data compression and data generation.
  arXiv  Detail & Related papers  (2023-05-17T18:00:28Z)
• A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors [60.489902135153415]
  This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement.
  arXiv  Detail & Related papers  (2021-11-26T06:33:29Z)
• Moment-Based Variational Inference for Stochastic Differential Equations [31.494103873662343]
  We construct the variational process as a controlled version of the prior process. We approximate the posterior by a set of moment functions. In combination with moment closure, the smoothing problem is reduced to a deterministic optimal control problem.
  arXiv  Detail & Related papers  (2021-03-01T13:20:38Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)
• The Reciprocal Bayesian LASSO [0.0]
  We consider a fully Bayesian formulation of the rLASSO problem, which is based on the observation that the rLASSO estimate for linear regression parameters can be interpreted as a Bayesian posterior mode estimate. On simulated and real datasets, we show that the Bayesian formulation outperforms its classical cousin in estimation, prediction, and variable selection.
  arXiv  Detail & Related papers  (2020-01-23T01:21:59Z)
• Variational Bayesian Methods for Stochastically Constrained System Design Problems [7.347989843033034]
  We study system design problems stated as parameterized programs with a chance-constraint set. We propose a variational Bayes-based method to approximately compute the posterior predictive integral.
  arXiv  Detail & Related papers  (2020-01-06T05:21:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.