|国家预印本平台
首页|Scalable Generalized Bayesian Online Neural Network Training for Sequential Decision Making

Scalable Generalized Bayesian Online Neural Network Training for Sequential Decision Making

Scalable Generalized Bayesian Online Neural Network Training for Sequential Decision Making

来源:Arxiv_logoArxiv
英文摘要

We introduce scalable algorithms for online learning and generalized Bayesian inference of neural network parameters, designed for sequential decision making tasks. Our methods combine the strengths of frequentist and Bayesian filtering, which include fast low-rank updates via a block-diagonal approximation of the parameter error covariance, and a well-defined posterior predictive distribution that we use for decision making. More precisely, our main method updates a low-rank error covariance for the hidden layers parameters, and a full-rank error covariance for the final layer parameters. Although this characterizes an improper posterior, we show that the resulting posterior predictive distribution is well-defined. Our methods update all network parameters online, with no need for replay buffers or offline retraining. We show, empirically, that our methods achieve a competitive tradeoff between speed and accuracy on (non-stationary) contextual bandit problems and Bayesian optimization problems.

Gerardo Duran-Martin、Leandro Sánchez-Betancourt、álvaro Cartea、Kevin Murphy

计算技术、计算机技术

Gerardo Duran-Martin,Leandro Sánchez-Betancourt,álvaro Cartea,Kevin Murphy.Scalable Generalized Bayesian Online Neural Network Training for Sequential Decision Making[EB/OL].(2025-06-13)[2025-07-21].https://arxiv.org/abs/2506.11898.点此复制

评论