An Equivalence between Bayesian Priors and Penalties in Variational Inference
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection
Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference
Variational Inference with Mixtures of Isotropic Gaussians
Amortized variational transdimensional inference
Synonymous Variational Inference for Perceptual Image Compression
Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.