Preferential Bayesian Optimization
نویسندگان
چکیده
Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimizing black-box functions where direct queries of the objective are expensive. In this paper we consider the case where direct access to the function is not possible, but information about user preferences is. Such scenarios arise in problems where human preferences are modeled, such as A/B tests or recommender systems. We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) which allows us to find the optimum of a latent function that can only be queried through pairwise comparisons, the so-called duels. PBO extends the applicability of standard BO ideas and generalizes previous discrete dueling approaches by modeling the probability of the winner of each duel by means of a Gaussian process model with a Bernoulli likelihood. The latent preference function is used to define a family of acquisition functions that extend usual policies used in BO. We illustrate the benefits of PBO in a variety of experiments, showing that PBO needs drastically fewer comparisons for finding the optimum. According to our experiments, the way of modeling correlations in PBO is key in obtaining this advantage.
منابع مشابه
Structure Learning in Bayesian Networks Using Asexual Reproduction Optimization
A new structure learning approach for Bayesian networks (BNs) based on asexual reproduction optimization (ARO) is proposed in this letter. ARO can be essentially considered as an evolutionary based algorithm that mathematically models the budding mechanism of asexual reproduction. In ARO, a parent produces a bud through a reproduction operator; thereafter the parent and its bud compete to survi...
متن کاملComparative Analysis of Machine Learning Algorithms with Optimization Purposes
The field of optimization and machine learning are increasingly interplayed and optimization in different problems leads to the use of machine learning approaches. Machine learning algorithms work in reasonable computational time for specific classes of problems and have important role in extracting knowledge from large amount of data. In this paper, a methodology has been employed to opt...
متن کاملRoBO: A Flexible and Robust Bayesian Optimization Framework in Python
Bayesian optimization is a powerful approach for the global derivative-free optimization of non-convex expensive functions. Even though there is a rich literature on Bayesian optimization, the source code of advanced methods is rarely available, making it difficult for practitioners to use them and for researchers to compare to and extend them. The BSD-licensed python package ROBO, released wit...
متن کاملEstimation of Products Final Price Using Bayesian Analysis Generalized Poisson Model and Artificial Neural Networks
Estimating the final price of products is of great importance. For manufacturing companies proposing a final price is only possible after the design process over. These companies propose an approximate initial price of the required products to the customers for which some of time and money is required. Here using the existing data of already designed transformers and utilizing the bayesian anal...
متن کاملMultiple utility constrained multi-objective programs using Bayesian theory
A utility function is an important tool for representing a DM’s preference. We adjoin utility functions to multi-objective optimization problems. In current studies, usually one utility function is used for each objective function. Situations may arise for a goal to have multiple utility functions. Here, we consider a constrained multi-objective problem with each objective having multiple utili...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017