paper-with-me

홈 › Papers

Stratified Bayesian Optimization

2016-02-07 · Saul Toscano-Palmerin, Peter I. Frazier

We consider derivative-free black-box global optimization of expensive noisy functions, when most of the randomness in the objective is produced by a few influential scalar random inputs. We present a new Bayesian global optimization algorithm, called Stratified Bayesian Optimization (SBO), which uses this strong dependence to improve performance. Our algorithm is similar in spirit to stratification, a technique from simulation, which uses strong dependence on a categorical representation of the random input to reduce variance. We demonstrate in numerical experiments that SBO outperforms state-of-the-art Bayesian optimization benchmarks that do not leverage this dependence.

📄 PDF Abstract BibTeX arXiv:1602.02338

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian Optimizationglobal-optimization

Similar Papers 제목 키워드 기반

A Stratified Analysis of Bayesian Optimization Methods

2016-03-31 · Ian Dewancker, Michael McCourt, Scott Clark, Patrick Hayes 외

Empirical analysis serves as an important complement to theoretical analysis for studying practical Bayesian optimization. Often empirical insights expose strengths and weaknesses inaccessible to theoretical analysis. We…

Bayesian OptimizationHyperparameter Optimization

Stratified Graphical Models - Context-Specific Independence in Graphical Models

2013-09-25 · Henrik Nyman, Johan Pensar, Timo Koski, Jukka Corander

Theory of graphical models has matured over more than three decades to provide the backbone for several classes of models that are used in a myriad of applications such as genetic mapping of diseases, credit risk evaluat…

Computer Security

Optimizing Large Language Models for Causality Assessment in Pharmacovigilance: Developing a Performance Metric as Objective for Bayesian Hyperparameter Optimization

2026-07-04 · Nicole Sonne Heckmann, Arnault-Quentin Vermillet, Søren Norlin Mølgaard, Manuela Del Castillo Suero 외 arxiv

Background: Growing individual case safety report (ICSR) volumes have intensified demand for scalable automated causality assessment. Large Language Models (LLMs) show promise, yet performance on clinically demanding tas…

Hyperparameter Optimization

Joint Graph Learning and Model Fitting in Laplacian Regularized Stratified Models

2023-05-04 · Ziheng Cheng, Junzi Zhang, Akshay Agrawal, Stephen Boyd

Laplacian regularized stratified models (LRSM) are models that utilize the explicit or implicit network structure of the sub-problems as defined by the categorical features called strata (e.g., age, region, time, forecas…

Few-Shot LearningGraph ClusteringGraph LearningRepresentation Learning+2

Marginal and simultaneous predictive classification using stratified graphical models

2014-01-31 · Henrik Nyman, Jie Xiong, Johan Pensar, Jukka Corander

An inductive probabilistic classification rule must generally obey the principles of Bayesian predictive inference, such that all observed and unobserved stochastic quantities are jointly modeled and the parameter uncert…

ClassificationGeneral Classification