统计学学术速递[2021.10.25]

统计学学术速递[2021.10.25]

访问arxivdaily.com获取含摘要速递,更有收藏、搜索等功能,涵盖CS|物理|数学|经济|统计|金融|生物|电气领域
同步公众号:arXiv每日学术速递,欢迎关注

stat统计学,共计39篇


【1】 Optimal randomized classification trees
标题:最优随机分类树
链接arxiv.org/abs/2110.1195
作者:Rafael Blanquero,Emilio Carrizosa,Cristina Molero-Río,Dolores Romero Morales
机构:Journal article, Please cite this article as:, Blanquero, R., Carrizosa, E., Molero-Río, C., & Romero Morales, D. (,)., Optimal randomized classification trees. Computers & Operations
备注:None

【2】 Missing the Point: Non-Convergence in Iterative Imputation Algorithms
标题:错失点:迭代填充算法中的不收敛
链接arxiv.org/abs/2110.1195
作者:Hanne Ida Oberman,Stef van Buuren,Gerko Vink
机构: and 3) there is not anEqual contribution 1Department of Methodology and Statis-tics, Utrecht University
备注:Presented at ICML 2020 ARTEMISS workshop. Associated GitHub repository: this https URL

【3】 Multimodel Bayesian Analysis of Load Duration Effects in Lumber Reliability
标题:木材可靠性载荷持续期效应的多模型贝叶斯分析
链接arxiv.org/abs/2110.1189
作者:Yunfeng Yang,Martin Lysy,Samuel W. K. Wong
机构:Department of Statistics and Actuarial Science, University of Waterloo
备注:15 pages, 2 figures

【4】 L-2 Regularized maximum likelihood for $β$-model in large and sparse networks
标题:大型稀疏网络中$β$-模型的L-2正则化最大似然
链接arxiv.org/abs/2110.1185
作者:Yu Zhang,Qiuping Wang,Yuan Zhang,Ting Yan,Jing Luo
机构:† Central China Normal University, The Ohio State University, § South-Central University for Nationalities

【5】 Variational Bayesian Approximation of Inverse Problems using Sparse Precision Matrices
标题:使用稀疏精度矩阵的反问题的变分贝叶斯逼近
链接arxiv.org/abs/2110.1184
作者:Jan Povala,Ieva Kazlauskaite,Eky Febrianto,Fehmi Cirak,Mark Girolami
机构:Department of Mathematics, Imperial College London, London, SW,AZ, UK, Department of Engineering, University of Cambridge, Cambridge, CB,PZ, UK, The Alan Turing Institute, London, NW,DB, UK

【6】 Testing network correlation efficiently via counting trees
标题:基于计数树的高效网络相关性测试
链接arxiv.org/abs/2110.1181
作者:Cheng Mao,Yihong Wu,Jiaming Xu,Sophie H. Yu

【7】 Probabilistic ODE Solutions in Millions of Dimensions
标题:百万维的概率常微分方程组
链接arxiv.org/abs/2110.1181
作者:Nicholas Krämer,Nathanael Bosch,Jonathan Schmidt,Philipp Hennig
机构:University of T¨ubingen, Max Planck Institute for Intelligent Systems, T¨ubingen, Germany

【8】 Probabilistic fine-tuning of pruning masks and PAC-Bayes self-bounded learning
标题:剪枝掩模的概率微调与PAC-Bayes自有界学习
链接arxiv.org/abs/2110.1180
作者:Soufiane Hayou,Bobby He,Gintare Karolina Dziugaite
机构:Department of Statistics, University of Oxford, MILA
备注:34 pages, 10 figures

【9】 Validation of point process predictions with proper scoring rules
标题:使用适当的评分规则验证点数过程预测
链接arxiv.org/abs/2110.1180
作者:Claudio Heinrich-Mertsching,Thordis L. Thorarinsdottir,Peter Guttorp,Max Schneider
机构:—, Thordis L., Thorarinsdottir, Norwegian Computing Center, Postboks, NO-, Oslo, Norway, Department of Statistics, Box , University of Washington, Seattle, WA , United States of, America, Correspondence, Computing Center, Postboks , Blindern, NO-, Oslo Oslo, Norway

【10】 Reconstruction of Sentinel-2 Time Series Using Robust Gaussian Mixture Models -- Application to the Detection of Anomalous Crop Development in wheat and rapeseed crops
标题:稳健高斯混合模型重建Sentinel-2时间序列--在小麦和油菜作物发育异常检测中的应用
链接arxiv.org/abs/2110.1178
作者:Florian Mouret,Mohanad Albughdadi,Sylvie Duthoit,Denis Kouamé,Guillaume Rieu,Jean-Yves Tourneret
机构:TerraNIS, Avenue de l’Europe, Ramonville-Saint-Agne, France, University of Toulouse IRIT-INP-ENSEEIHT TéSA, Rue Charles Camichel, Toulouse, France, University of Toulouse IRIT-UPS, Route de Narbonne, Toulouse Cedex , France,

【11】 Additive Density-on-Scalar Regression in Bayes Hilbert Spaces with an Application to Gender Economics
标题:贝叶斯-希尔BERT空间中的加性标量密度回归及其在性别经济学中的应用
链接arxiv.org/abs/2110.1177
作者:Eva-Maria Maier,Almond Stöcker,Bernd Fitzenberger,Sonja Greven
机构:Greven, Chair of Statistics, School of Business and Economics, Humboldt-Universit¨at zu Berlin, IAB (Institute for Employment Research), Nuremberg, Germany

【12】 The Equilibrium Hypothesis: Rethinking implicit regularization in Deep Neural Networks
标题:均衡假设:对深度神经网络隐式正则化的再思考
链接arxiv.org/abs/2110.1174
作者:Yizhang Lou,Chris Mingard,Soufiane Hayou
机构:St. John’s College, University of Oxford, Oxford, UK, Department of Chemistry, Department of Mathematics, National University of Singapore

【13】 Adaptive random neighbourhood informed Markov chain Monte Carlo for high-dimensional Bayesian variable
标题:高维贝叶斯变量的自适应随机邻域信息马尔可夫链蒙特卡罗方法
链接arxiv.org/abs/2110.1174
作者:Xitong Liang,Samuel Livingstone,Jim Griffin
机构:Department of Statistical Science, University College London, UK
备注:27 pages + 27 pages of Supplementary material, 13 figures, 3 tables

【14】 Focusing on Difficult Directions for Learning HMC Trajectory Lengths
标题:关注学习HMC轨迹长度的难点方向
链接arxiv.org/abs/2110.1157
作者:Pavel Sountsov,Matt D. Hoffman
机构:Google Research

【15】 Temporal Point Process Graphical Models
标题:时点过程图形化模型
链接arxiv.org/abs/2110.1156
作者:Yalong Lyu,Huiyuan Wang,Wei Lin
机构:School of Mathematical Sciences, Peking University, China
备注:21 pages,5 figures

【16】 Merging Two Cultures: Deep and Statistical Learning
标题:融合两种文化:深度学习与统计学习
链接arxiv.org/abs/2110.1156
作者:Anindya Bhadra,Jyotishka Datta,Nick Polson,Vadim Sokolov,Jianeng Xu
机构:First Draft: Nov , This Draft: Oct
备注:arXiv admin note: text overlap with arXiv:2106.14085

【17】 Generalized Results for the Existence and Consistency of the MLE in the Bradley-Terry-Luce Model
标题:关于Bradley-Terry-Luce模型中极大似然估计存在性和相合性的推广结果
链接arxiv.org/abs/2110.1148
作者:Heejong Bong,Alessandro Rinaldo
机构:Department of Statistics and Data Sciences, Carnegie Mellon University, Pittsburgh, PA

【18】 Conditioning of Random Feature Matrices: Double Descent and Generalization Error
标题:随机特征矩阵的条件化:双下降和泛化误差
链接arxiv.org/abs/2110.1147
作者:Zhijun Chen,Hayden Schaeffer
机构:Department of Mathematical Sciences, Carnegie Mellon University, Pittsburgh, PA ,.

【19】 Combining Parametric and Nonparametric Models to Estimate Treatment Effects in Observational Studies
标题:结合参数模型和非参数模型估计观察性研究中的治疗效果
链接arxiv.org/abs/2110.1134
作者:Daniel Daly-Grafstein,Paul Gustafson
机构:Department of Statistics, University of British Columbia
备注:34 pages, 5 figures

【20】 Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff
标题:潜在模型的对抗性稳健性:重新审视健壮性与标准精确度之间的权衡
链接arxiv.org/abs/2110.1195
作者:Adel Javanmard,Mohammad Mehrabi

【21】 Learning Proposals for Practical Energy-Based Regression
标题:实用能量型回归的学习建议
链接arxiv.org/abs/2110.1194
作者:Fredrik K. Gustafsson,Martin Danelljan,Thomas B. Schön
机构:Dept. of Information Technology, Uppsala University, Sweden, Computer Vision Lab, ETH Zürich, Switzerland
备注:Code is available at this https URL

【22】 On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
标题:论机器遗忘的可审计算法定义的必要性
链接arxiv.org/abs/2110.1189
作者:Anvith Thudi,Hengrui Jia,Ilia Shumailov,Nicolas Papernot
机构:University of Toronto and Vector Institute

【23】 Conditional Gaussian PAC-Bayes
标题:条件高斯PAC-贝叶斯
链接arxiv.org/abs/2110.1188
作者:Eugenio Clerico,George Deligiannidis,Arnaud Doucet
机构:Department of Statistics, University of Oxford, UK

【24】 Tight and Robust Private Mean Estimation with Few Users
标题:少用户情况下紧致稳健的私人均值估计
链接arxiv.org/abs/2110.1187
作者:Hossein Esfandiari,Vahab Mirrokni,Shyam Narayanan
备注:38 pages

【25】 GeneDisco: A Benchmark for Experimental Design in Drug Discovery
标题:GeneDisco:药物发现实验设计的基准
链接arxiv.org/abs/2110.1187
作者:Arash Mehrjou,Ashkan Soleymani,Andrew Jesson,Pascal Notin,Yarin Gal,Stefan Bauer,Patrick Schwab
机构:GlaxoSmithKline, Artificial Intelligence & Machine Learning, MIT, Department of Computer Science, University of Oxford, CIFAR Azrieli Global Scholar, KTH Stockholm

【26】 Polynomial-Time Sum-of-Squares Can Robustly Estimate Mean and Covariance of Gaussians Optimally
标题:多项式时间平方和最优稳健估计高斯均值和协方差
链接arxiv.org/abs/2110.1185
作者:Pravesh K. Kothari,Peter Manohar,Brian Hu Zhang
机构:Computer Science Department, Carnegie Mellon University, Pittsburgh, USA

【27】 Probabilistic Numerical Method of Lines for Time-Dependent Partial Differential Equations
标题:含时偏微分方程的概率直线数值方法
链接arxiv.org/abs/2110.1184
作者:Nicholas Krämer,Jonathan Schmidt,Philipp Hennig
机构:University of T¨ubingen, Max Planck Institute for Intelligent Systems, T¨ubingen, Germany

【28】 Identifiability of local and global features of phylogenetic networks from average distances
标题:从平均距离识别系统发育网络的局部和全局特征
链接arxiv.org/abs/2110.1181
作者:Jingcheng Xu,Cécile Ané
机构:Department of Statistics, University of Wisconsin - Madison, Madison, WI, United States., Department of Botany, University of Wisconsin - Madison

【29】 Model, sample, and epoch-wise descents: exact solution of gradient flow in the random feature model
标题:模型、样本和时代递减:随机特征模型中梯度流的精确解
链接arxiv.org/abs/2110.1180
作者:Antoine Bodin,Nicolas Macris
机构:&, Communication Theory Laboratory, School of Computer and Communication Sciences, Ecole Polytechnique Fédérale de Lausanne

【30】 Sinkformers: Transformers with Doubly Stochastic Attention
标题:辛克Transformer:具有双重随机注意力的Transformer
链接arxiv.org/abs/2110.1177
作者:Michael E. Sander,Pierre Ablin,Mathieu Blondel,Gabriel Peyré
机构:Ecole Normale Sup´erieure, DMA, Paris, France, CNRS, France, Google Research, Brain team
备注:26 pages

【31】 Clustering of Bank Customers using LSTM-based encoder-decoder and Dynamic Time Warping
标题:基于LSTM编解码器和动态时间规整的银行客户聚类
链接arxiv.org/abs/2110.1176
作者:Ehsan Barkhordar,Mohammad Hassan Shirali-Shahreza,Hamid Reza Sadeghi
机构:Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran, M. Hassan Shirali-Shahreza, H. Reza Sadeghi

【32】 Variational Wasserstein Barycenters with c-Cyclical Monotonicity
标题:具有c-循环单调性的变分Wasserstein重心
链接arxiv.org/abs/2110.1170
作者:Jinjin Chi,Zhiyao Yang,Jihong Ouyang,Ximing Li
机构:Jilin University

【33】 Differentially Private Coordinate Descent for Composite Empirical Risk Minimization
标题:复合经验风险最小化的微分私有坐标下降法
链接arxiv.org/abs/2110.1168
作者:Paul Mangold,Aurélien Bellet,Joseph Salmon,Marc Tommasi
机构:Univ. Lille, Inria, CNRS, Centrale Lille, UMR , - CRIStAL, F-, Lille, France, IMAG, Univ Montpellier, CNRS, Montpellier, France, Institut Universitaire, de France (IUF), Univ. Lille, CNRS, Inria, Centrale Lille
备注:27 pages, 2 figures

【34】 Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes
标题:带定义点过程的分批贝叶斯优化的多样化抽样
链接arxiv.org/abs/2110.1166
作者:Elvis Nava,Mojmír Mutný,Andreas Krause
机构:Mojm´ır Mutn´y, ETH AI Center, ETH Zurich, Department of Computer Science

【35】 Fractional Modeling in Action: A Survey of Nonlocal Models for Subsurface Transport, Turbulent Flows, and Anomalous Materials
标题:作用中的分形建模:地下传输、湍流和异常材料的非局部模型综述
链接arxiv.org/abs/2110.1153
作者:Jorge Suzuki,Mamikon Gulian,Mohsen Zayernouri,Marta D'Elia
机构:Received: date Accepted: date
备注:75 pages, 16 figures

【36】 Power Transformer Fault Diagnosis with Intrinsic Time-scale Decomposition and XGBoost Classifier
标题:基于本征时间尺度分解和XGBoost分类器的电力Transformer故障诊断
链接arxiv.org/abs/2110.1146
作者:Shoaib Meraj Sami,Mohammed Imamul Hassan Bhuiyan
机构:Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka , Bangladesh
备注:09 pages, 3 figures, conference

【37】 An EMD-based Method for the Detection of Power Transformer Faults with a Hierarchical Ensemble Classifier
标题:基于经验模态分解的分层集成分类器电力Transformer故障检测方法
链接arxiv.org/abs/2110.1145
作者:Shoaib Meraj Sami,Mohammed Imamul Hassan Bhuiyan
机构:Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology, Dhaka-, Bangladesh
备注:04 pages, 04 figures, Conference

【38】 Towards Noise-adaptive, Problem-adaptive Stochastic Gradient Descent
标题:走向噪声自适应、问题自适应的随机梯度下降
链接arxiv.org/abs/2110.1144
作者:Sharan Vaswani,Benjamin Dubois-Taine,Reza Babanezhad
机构:Amii, University of Alberta, Universit´e Paris-Saclay, SAIT AI lab, Montreal

【39】 SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
标题:SOSP:基于二阶结构剪枝的全局相关性高效捕获
链接arxiv.org/abs/2110.1139
作者:Manuel Nonnenmacher,Thomas Pfeil,Ingo Steinwart,David Reeb
机构:Bosch Center for Artificial Intelligence (BCAI), Robert Bosch GmbH, Renningen, Germany, Institute for Stochastics and Applications, University of Stuttgart, Stuttgart, Germany

机器翻译,仅供参考


访问arxivdaily.com获取含摘要速递,更有收藏、搜索等功能,涵盖CS|物理|数学|经济|统计|金融|生物|电气领域
同步公众号:arXiv每日学术速递,欢迎关注
发布于 2021-10-25 09:40