554期

最新文章

• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy AI翻译
  作者：Zhong, Han; Deng, Xun; Fang, Ethan X.; Yang, Zhuoran; Wang, Zhaoran; Li, Runze
  作者单位：Peking University; Chinese Academy of Sciences; University of Science & Technology of China, CAS; Duke University; Yale University; Northwestern University; Pennsylvania Commonwealth System of Higher Education (PCSHE); Pennsylvania State University; Pennsylvania State University - University Park
  摘要：While deep reinforcement learning has achieved tremendous successes in various applications, most existing works focus on maximizing the expected value of total return and ignore its inherent stochasticity. Such stochasticity is also known as the aleatoric uncertainty and is closely related to the notion of risk. This work makes the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. Particularly, we focus on a var...
• Distributional Off-Policy Evaluation with Deep Quantile Process Regression AI翻译
  作者：Kuang, Qi; Wang, Chao; Jiao, Yuling; Zhou, Fan
  作者单位：Jiangxi University of Finance & Economics; Jiangxi University of Finance & Economics; Shanghai University of Finance & Economics; Wuhan University; Wuhan University
  摘要：This article investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of the total return, as in most existing OPE methods, we aim to estimate the entire return distribution. To this end, we introduce a quantile-based approach for OPE using deep quantile process regression, presenting a novel algorithm called Deep Quantile Process regression-based Off-Policy Evaluation (DQPOPE). We provide new theoretical insights in...
• Blessing from Human-AI Interaction: Super Policy Learning in Confounded Environments AI翻译
  作者：Wang, Jiayi; Shi, Chengchun; Qi, Zhengling
  作者单位：University of Texas System; University of Texas Dallas; University of London; London School Economics & Political Science; George Washington University
  摘要：As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this article, we introduce the paradigm of super policy learning that takes advantage of Human-AI interaction for data driven sequential decision making. This approach uses the observed action, either from AI or humans, as input for achieving a stronger oracle in policy learning for the decision ...
• On a Class of Sobolev Tests for Symmetry, their Detection Thresholds, and Asymptotic Powers AI翻译
  作者：Garcia-Portugues, Eduardo; Paindaveine, Davy; Verdebout, Thomas
  作者单位：Universidad Carlos III de Madrid; Universite Libre de Bruxelles; Universite Libre de Bruxelles
  摘要：We consider a broad class of symmetry hypothesis testing problems that includes the problems of testing uniformity or rotational symmetry on the hypersphere Sd-1, as well as the problem of testing sphericity in R-d. For this class, we study the null and non-null behaviors of Sobolev tests, with emphasis on their consistency rates and corresponding asymptotic powers. Our main results show that: (i) Sobolev tests exhibit a detection threshold that depends not only on the coefficients defining th...
• Seminal Ideas and Controversies in Statistics AI翻译
  作者：Williams, Jonathan P.
  作者单位：North Carolina State University
• Frequency-Band Estimation of the Number of Factors AI翻译
  作者：Avarucci, Marco; Cavicchioli, Maddalena; Forni, Mario; Zaffaroni, Paolo
  作者单位：University of Glasgow; Universita di Modena e Reggio Emilia; Imperial College London; Sapienza University Rome
  摘要：We introduce consistent estimators for the number of shocks driving large-dimensional dynamic factor models. Our estimator can be applied to single frequencies and specific frequency bands, making it suitable for disentangling shocks affecting dynamic models with a factor model representation. Noticeably, our estimator requires the time-series and cross-section sizes to diverge simultaneously without any constraint and it is free of nuisance parameters, such as penalization terms. Our methodol...
• Optimal Run Order for Order-of-Addition Experiments AI翻译
  作者：Wang, Chunyan; Peng, Jiayu; Lin, Dennis K. J.
  作者单位：Renmin University of China; Renmin University of China; Alphabet Inc.; Google Incorporated; Purdue University System; Purdue University
  摘要：Order-of-addition experiments have emerged as a cornerstone in modern experimental design, yet the critical role of run-order has been entirely neglected in the literature. This oversight is surprising, given that the run order can significantly influence the cost, efficiency, and validity of the experiment. Certain run orders are inherently more economical and effective, while suboptimal orders may introduce unnecessary complexities or compromise results. To ensure experimental integrity, an ...
• Cluster-Randomized Trials with Cross-Cluster Interference AI翻译
  作者：Leung, Michael P.
  作者单位：University of California System; University of California Santa Cruz
  摘要：The literature on cluster-randomized trials typically allows for interference within but not across clusters. This may be implausible when units are irregularly distributed across space without well-separated communities, as clusters in such cases may not align with significant geographic, social, or economic divisions. This article develops methods for reducing bias due to cross-cluster interference. We first propose an estimation strategy that excludes units not surrounded by clusters assign...
• Efficient Human-in-the-Loop Active Learning: A Novel Framework for Data Labeling in AI Systems AI翻译
  作者：Huang, Yiran; Yang, Jian-Feng; Fu, Haoda
  作者单位：Nankai University; University of North Carolina; University of North Carolina Chapel Hill; University of North Carolina School of Medicine
  摘要：Modern AI systems rely heavily on labeled data, yet labeling is often expensive and labor-intensive, especially when requiring special skills such as reading radiology images by physicians. To most efficiently use experts' time for data labeling, one promising approach is human-in-the-loop active learning. However, traditional active learning methods are limited to single-label queries and fail to leverage more flexible query types in many real-world settings. In this work, we propose a novel ...
• Construction of Asymmetric Nested Orthogonal Arrays AI翻译
  作者：Pang, Shanqi; Lin, Xiao; Ai, Mingyao; Chien, Peter
  作者单位：Henan Normal University; Peking University; Peking University; University of Wisconsin System; University of Wisconsin Madison; Anyang Normal University
  摘要：Nested orthogonal arrays (NOAs), which consist of a pair of orthogonal arrays with one array nested within the other, are extensively used in computer experiments and statistics. They have diverse applications, including data fusion, digital twins, model validation, sequential model evaluation, stochastic programming, chance-constraint problems, nonparametric function estimation, and parameter linking. We propose several general methods for constructing asymmetric NOAs with flexible run sizes,...