Modern retrieval systems are often driven by an underlying machine learning model. The goal of such systems is to identify and possibly rank the few most relevant items for a given query or context. Thus, such systems are typically evaluated using a ranking-based performance metric such as the area under the precision-recall curve, the $F_β$ score, precision at fixed recall, etc. Obviously, it is desirable to train such systems to optimize the metric of interest.
In practice, due to the scalability limitations of existing approaches for optimizing such objectives, large-scale retrieval systems are instead trained to maximize classification accuracy, in the hope that performance as measured via the true objective will also be favorable. In this work we present a unified framework that, using straightforward building block bounds, allows for highly scalable optimization of a wide range of ranking-based objectives. We demonstrate the advantage of our approach on several real-life retrieval problems that are significantly larger than those considered in the literature, while achieving substantial improvement in performance over the accuracy-objective baseline.
Optimizing Non-decomposable Measures with Deep Networks
University of Oxford（牛津大学）；IIT Kanpur（印度理工学院坎普尔分校）；Qatar Computing Research Institute（卡塔尔计算研究所）；Istituto di Scienza e Tecnologia dell’Informazione（意大利信息科学与技术研究所）
Generative Multi-Objective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design
Department of Chemical and Biological Engineering, University of Wisconsin--Madison, Madison, Wisconsin 53706, United States（化学与生物工程系，威斯康星大学麦迪逊分校）；Department of Chemical and Biomolecular Engineering, The Ohio State University, Columbus, Ohio 43210, United States（化学与生物分子工程系，俄亥俄州立大学）
Top-N-Rank: A Scalable List-wise Ranking Method for Recommender Systems
Pennsylvania State University（宾夕法尼亚州立大学）；South China University of Technology（华南理工大学）
我们提出了Top-N-Rank，一种新颖的列表式学习排名模型，用于可靠地推荐N个排名靠前的项目。所提出的模型优化了广泛使用的折扣累积增益（DCG）目标函数的变体，其在两个重要方面不同于DCG：（i）它将DCG的评估仅限于排名列表中的前N个项目，从而消除了低排名项目对学习的排名函数的影响;以及（ii）它结合了允许模型利用具有不同可靠性或可信度级别的多种类型的隐式反馈的权重。由于得到的目标函数是非光滑的，因此优化具有挑战性，我们考虑使用传统的S形函数和校正线性单元（ReLU）对目标函数进行两个光滑近似。我们提出了一个家庭的学习排名算法（Top-N-Rank），工作与任何光滑的目标函数。然后，引入了一个更有效的变体Top-N-Rank.ReLU，该变体有效地利用了ReLU函数的性质，将Top-N-Rank的计算复杂性从用户评分的平均项目数的二次降低到线性。我们使用两个广泛使用的基准测试，即MovieLens数据集和Amazon Video Games数据集的实验结果表明：（i）目标函数的“top-N截断”大大提高了前N个推荐的排名质量;（ii）与使用sigmoid相比，使用ReLU来平滑目标函数在排名质量和运行时间方面都有显着改善;以及（iii）Top-N-Rank.ReLU在排名质量方面大大优于表现良好的列表式排名方法。
A Scalable Gradient-Based Optimization Framework for Sparse Minimum-Variance Portfolio Selection
School of Mathematics and Statistics（数学与统计学学院）；University of New South Wales（新南威尔士大学）；School of Mathematical and Physical Sciences（数学与物理科学学院）；University of Technology Sydney（技术大学悉尼分校）；Bayes Business School（贝叶斯商学院）；City St George’s, University of London（伦敦大学城圣乔治学院）；Faculty of Science and Engineering（科学与工程学院）；Macquarie University（麦考瑞大学）
