In landscape-aware algorithm selection problem, the effectiveness of feature-based predictive models strongly depends on the representativeness of training data for practical applications. In this work, we investigate the potential of randomly generated functions (RGF) for the model training, which cover a much more diverse set of optimization problem classes compared to the widely-used black-box optimization benchmarking (BBOB) suite. Correspondingly, we focus on automated algorithm configuration (AAC), that is, selecting the best suited algorithm and fine-tuning its hyperparameters based on the landscape features of problem instances. Precisely, we analyze the performance of dense neural network (NN) models in handling the multi-output mixed regression and classification tasks using different training data sets, such as RGF and many-affine BBOB (MA-BBOB) functions. Based on our results on the BBOB functions in 5d and 20d, near optimal configurations can be identified using the proposed approach, which can most of the time outperform the off-the-shelf default configuration considered by practitioners with limited knowledge about AAC. Furthermore, the predicted configurations are competitive against the single best solver in many cases. Overall, configurations with better performance can be best identified by using NN models trained on a combination of RGF and MA-BBOB functions.
The Importance of Landscape Features for Performance Prediction of Modular CMA-ES Variants
Jožef Stefan Institute(约泽夫·斯蒂芬研究所);Jožef Stefan International Postgraduate School(约泽夫·斯蒂芬国际研究生院);Leiden Institute for Advanced Computer Science(莱顿高级计算机科学研究所);Sorbonne Université(索邦大学);CNRS(法国国家科学研究中心)
SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data
Nanjing University(南京大学);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院)
From the String Landscape to the Mathematical Landscape: a Machine-Learning Outlook
London Institute for Mathematical Sciences(伦敦数学科学研究所);Royal Institution of Great Britain(英国皇家学会);University of Oxford(牛津大学);City, University of London(伦敦城市大学);NanKai University(南开大学)
Automated Constitutive Model Discovery by Pairing Sparse Regression Algorithms with Model Selection Criteria
Institute of Applied Mechanics, Division Data-Driven Modeling of Mechanical Systems, Technische Universität Braunschweig(应用力学研究所,数据驱动机械系统建模 division,勃兰登堡工业大学);Computational Mechanics Group, Eidgenössische Technische Hochschule Zürich(计算力学组,瑞士苏黎世联邦理工学院)
Automated SSIM Regression for Detection and Quantification of Motion Artefacts in Brain MR Images
University Hospital Magdeburg(马格德堡大学医院);Otto von Guericke University(奥托·冯·格里克大学);Human Technopole(人类技术中心);University of L’Aquila(拉奎拉大学);Center for Behavioral Brain Sciences(行为脑科学中心);German Center for Neurodegenerative Disease(德国神经退行性疾病中心)
MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI
Department of Surgical Sciences, Uppsala University(乌普萨拉大学外科学系);Department of Information Technology, Uppsala University(乌普萨拉大学信息技术系);Antaros Medical AB
Local Law 144: A Critical Analysis of Regression Metrics
Holistic AI
在招聘中使用自动化决策工具已受到越来越多的关注。2021年11月,纽约市议会通过了一项立法(第144号地方法),要求对自动就业决策工具进行偏见审计。从2023年4月15日起,使用自动化工具招聘或晋升员工的公司必须由独立实体对这些系统进行审计。要求审计员计算偏倚指标,以比较不同群体的结果,至少基于性别/性别和种族/民族类别。Local Law 144为回归任务(自动化系统用连续范围的值对候选人进行评分的场景)提出了新的偏差度量。该立法的前一版本提出了一个偏见指标,比较了不同群体的平均得分。新修订的偏见指标比较了每组中超过中位数的候选人比例。在本文中,我们认为,这两个指标未能捕捉整个域的分布差异,因此不能可靠地检测偏差。我们首先介绍两个指标,作为立法指标的可能替代品。然后,我们比较这些指标在一系列的理论例子,立法提出的指标似乎低估了偏见。最后,我们研究了真实的数据,并表明立法指标在现实世界的招聘应用程序中同样会失败。
Deep-ELA: Deep Exploratory Landscape Analysis with Self-Supervised Pretrained Transformers for Single- and Multi-Objective Continuous Optimization Problems
Paderborn University(帕德博恩大学);TU Dresden(德累斯顿工业大学);ScaDS.AI Dresden/Leipzig(德累斯顿/莱比锡数据科学与人工智能中心);University of Twente(特文特大学)
AutoSINDy: Discovery of Nonlinear Dynamics with Automated Library Construction
Data Science and Analytics Institute, University of Oklahoma, Norman, OK, USA(数据科学与分析研究所,俄克拉荷马大学,诺曼,OK,USA);School of Industrial and Systems Engineering, University of Oklahoma, Norman, OK, USA(工业与系统工程学院,俄克拉荷马大学,诺曼,OK,USA)
用有限的人力分析更好的时间序列是学术界和工业界感兴趣的。在业务场景的驱动下,我们为WSDM Cup 2020组织了第一次自动时间序列回归挑战赛(AutoSeries)。我们提出了它的设计,分析和事后实验。代码提交要求排除了参与者在硬件和时间限制下跨许多数据集进行任何手动干预、测试解决方案的自动化机器学习功能的可能性。我们准备了来自不同应用领域(销售、电力消耗、空气质量、交通和停车)的10个数据集,其中包括缺失数据、混合连续变量和分类变量以及各种采样率。每个数据集都被分成训练序列和测试序列(这是流式的,允许模型不断适应)。时间序列回归的设定与经典预测的不同之处在于,当前时间的协变量是已知的。参与者在解决这个AutoSeries问题方面取得了很大的进步,从样本提交的性能跳跃以及与AutoGluon的事后比较可以看出。使用了简单而有效的方法,基于特征工程,LightGBM和随机搜索超参数调整,解决了挑战的各个方面。我们的事后分析显示,提供额外的时间并没有产生显着的改善。获奖者的代码是开源的https://github.com/NehzUx/AutoSeries。
Conditional Mean and Variance Estimation via \textit{k}-NN Algorithm with Automated Variance Selection
Harvard T.H. Chan School of Public Health(哈佛大学T.H. Chan公共卫生学院);University of Santiago de Compostela(圣西蒙大学);University of California, Los Angeles(加州大学洛杉矶分校)
Semantic Latent Space Regression of Diffusion Autoencoders for Vertebral Fracture Grading
Technical University of Munich(慕尼黑工业大学);Klinikum Rechts der Isar (Technical University of Munich)(慕尼黑工业大学伊萨尔河右岸医院);University of Munich(慕尼黑大学);Klinikum der Universität München(慕尼黑大学医院);Johns Hopkins University(约翰斯·霍普金斯大学)
Institute of Artificial Intelligence, Leibniz University Hannover(汉诺威莱布尼茨大学人工智能学院);Institute for Information Processing, Leibniz University Hannover(汉诺威莱布尼茨大学信息处理学院)
Loss Landscape Degeneracy and Stagewise Development in Transformers
Timaeus;Department of Computer Science, University of Oxford(计算机科学系,牛津大学);Department of Econometrics and Business Statistics, Monash University(计量经济学与商业统计系,墨尔本大学);School of Mathematics and Statistics, the University of Melbourne(数学与统计学系,墨尔本大学)
Automated Model Selection for Generalized Linear Models
Institute of Computer Technology, TU Wien(维也纳技术大学计算机技术研究所);Department of Statistics, University of Klagenfurt(克雷格弗特大学统计学系);Institute of Statistics and Mathematical Methods in Economics, TU Wien(维也纳技术大学统计学与经济学数学方法研究所)