Information Theoretic Bayesian Optimization over the Probability Simplex
Department of Economics, Management and Statistics University of Milan, Bicocca(经济管理统计系米兰大学Bicocca分校);Department of Robotics, Perception and Learning KTH Royal Institute of Technology(机器人感知与学习系皇家理工学院KTH);University of Milan, Bicocca Milan, Italy(米兰大学Bicocca分校);KTH Royal Institute of Technology Stockholm, Sweden(皇家理工学院KTH 斯德哥尔摩瑞典)
Federico Pavesi, Antonio Candelieri, Noémie Jaquier
Bayesian optimization is a data-efficient technique that has been shown to be extremely powerful to optimize expensive, black-box, and possibly noisy objective functions. Many applications involve optimizing probabilities and mixtures which naturally belong to the probability simplex, a constrained non-Euclidean domain defined by non-negative entries summing to one. This paper introduces $α$-GaBO, a novel family of Bayesian optimization algorithms over the probability simplex. Our approach is grounded in information geometry, a branch of Riemannian geometry which endows the simplex with a Riemannian metric and a class of connections. Based on information geometry theory, we construct Matérn kernels that reflect the geometry of the probability simplex, as well as a one-parameter family of geometric optimizers for the acquisition function. We validate our method on benchmark functions and on a variety of real-world applications including mixtures of components, mixtures of classifiers, and a robotic control task, showing its increased performance compared to constrained Euclidean approaches.
Geometry-Aware Bayesian Quantification via Compositional Data Analysis
Istituto di Scienza e Tecnologie dell’Informazione Consiglio Nazionale delle Ricerche(国家研究委员会信息科学与技术研究所);Artificial Intelligence Center University of Oviedo(奥维耶多大学人工智能中心)
Approximate Bayesian Computation of Bézier Simplices
RIKEN Interdisciplinary Theoretical and Mathematical Sciences Program(理化学研究所跨学科理论与数学科学项目);RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Keio University(庆应义塾大学);Fujitsu Limited(富士通株式会社);Tokyo Institute of Technology(东京工业大学);KLab Inc.(KLab株式会社)
Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning
Universidad Tecnológica Nacional(国立科技大学);GISIQ, Facultad Regional Villa María, UTN(国立科技大学维拉玛丽亚地区学院 GISIQ);CIT Villa María, CONICET-UNVM(国家科学与技术研究理事会-国立维拉玛丽亚大学维拉玛丽亚科技研究中心);INGAR, CONICET-UTN(国家科学与技术研究理事会-国立科技大学工业自动化研究所)
Stable Global Weighting of Flow Mixtures using Simplex Exponential Moving Average
School of Computer Science and Informatics, Cardiff University(卡迪夫大学计算机科学与信息学学院);Department of Computer Engineering, Turkish Air Force Academy, National Defence University(土耳其空军学院计算机工程系,国家防卫大学)
A Layered Simplex Architecture for Large Alphabets
School of Electrical and Computer Engineering(电气与计算机工程学院);Tel Aviv University(特拉维夫大学);School of Computer and Communication Sciences(计算机与通信科学学院);EPFL(洛桑联邦理工学院)
An Information-Theoretic Analysis of Bayesian Reinforcement Learning
KTH Royal Institute of Technology(瑞典皇家理工学院)
基于Xu和Raginksy [1]为监督学习问题引入的框架,我们研究了基于模型的贝叶斯强化学习问题的最佳可实现性能。为此,我们将最小贝叶斯后悔(MBR)定义为通过从收集的数据中学习或通过了解环境及其动态可获得的最大预期累积奖励之间的差异。我们专门这个定义的强化学习问题建模为马尔可夫决策过程(MDP)的核心参数是未知的代理和其不确定性表示的先验分布。给出了一种推导MBR上界的方法,并给出了基于相对熵和Wasserstein距离的具体上界。然后,我们专注于两个特殊的情况下,MDP,多臂强盗问题(MAB)和在线优化与部分反馈问题。对于后一个问题,我们证明了我们的边界可以从Russo和Van Roy [2]的当前信息论边界以下恢复。
Information-theoretic limits of Bayesian network structure learning
Purdue University(普渡大学)
在本文中,我们研究了学习贝叶斯网络(BN)的结构,离散以及连续的随机变量,从有限数量的样本的信息理论的限制。我们发现,任何程序恢复正确的结构所需的最小样本数分别为$Ω(m)$和$Ω(k \log m + (k^2/m))$增长为非稀疏和稀疏BN,其中$m$是变量的数量和$k$是每个节点的父母的最大数量。我们提供了一个简单的配方,基于扩展的Fano不等式,以获得信息理论的限制,任何指数家庭BN的结构恢复。我们实例化我们的结果为特定的条件分布在指数家庭的基本限制学习各种常用的BN,如条件概率表为基础的网络,高斯BN,噪声或网络和逻辑回归网络的特征。在获得我们的主要结果的途中,我们获得了稀疏和非稀疏本质DAG的数量上的严格界限。最后,作为一个副产品,我们恢复稀疏变量选择逻辑回归的信息理论限制。