PAC-Bayesian Theory Meets Bayesian Inference
원문 초록
We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generalization risk bounds maximizes the Bayesian marginal likelihood. This provides an alternative explanation to the Bayesian Occam's razor criteria, under the assumption that the data is generated by an i.i.d distribution. Moreover, as the negative log-likelihood is an unbounded loss function, we motivate and propose a PAC-Bayesian theorem tailored for the sub-gamma loss family, and we show that our approach is sound on classical Bayesian linear regression tasks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Bayesian Data Sketching for Varying Coefficient Regression Models
Normalizing Flow Regression for Bayesian Inference with Offline Likelihood Evaluations
Statistical Machine Learning for Astronomy -- A Textbook
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net Models
Active Learning for Manifold Gaussian Process Regression
Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace Inference
토론
이 논문과 연결된 포럼 글이 아직 없습니다.