553期

最新文章

• Data Thinning for Poisson Factor Models and its Applications AI翻译
  作者：Wang, Zhijing; Xu, Peirong; Zhao, Hongyu; Wang, Tao
  作者单位：Shanghai Jiao Tong University; Yale University; Shanghai Jiao Tong University; Shanghai Jiao Tong University
  摘要：The Poisson factor model is a powerful tool for dimension reduction and visualization of large-scale count datasets across diverse domains. Despite the availability of efficient algorithms for estimating factors and loadings, existing methods either require prior knowledge of the number of factors, or resort to ad hoc criteria for its determination. This article proposes a novel data-driven criterion called Information Criterion via Data Thinning (ICDT), leveraging the thinning property of the...
• Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization AI翻译
  作者：Meng, Xuran; Cao, Yuan; Wang, Weichen
  作者单位：University of Michigan System; University of Michigan; University of Hong Kong
  摘要：Portfolio optimization aims at constructing a realistic portfolio with significant out-of-sample performance, which is typically measured by the out-of-sample Sharpe ratio. However, due to in-sample optimism, it is inappropriate to use the in-sample estimated covariance to evaluate the out-of-sample Sharpe, especially in the high dimensional settings. In this article, we propose a novel method to estimate the out-of-sample Sharpe ratio using only in-sample data, based on random matrix theory. ...
• Towards Better Statistical Understanding of Watermarking LLMs AI翻译
  作者：Cai, Zhongze; Liu, Shang; Wang, Hanzhao; Zhong, Huaiyang; Li, Xiaocheng
  作者单位：Imperial College London; University of Sydney; Virginia Polytechnic Institute & State University
  摘要：In this article, we study the problem of watermarking large language models (LLMs). We consider the tradeoff between model distortion and detection ability and formulate it as a constrained optimization problem based on the red-green list watermarking algorithm. We show that the optimal solution to the optimization problem enjoys a nice analytical property which provides a better understanding and inspires the algorithm design for the watermarking process. We develop an online dual gradient as...
• Causality-Oriented Robustness: Exploiting General Noise Interventions AI翻译
  作者：Shen, Xinwei; Buhlmann, Peter; Taeb, Armeen
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich; University of Washington; University of Washington Seattle
  摘要：Since distribution shifts are common in real-world applications, there is a pressing need to develop prediction models that are robust against such shifts. Existing frameworks, such as empirical risk minimization or distributionally robust optimization, either lack generalizability for unseen distributions or rely on postulated distance measures. Alternatively, causality offers a data-driven and structural perspective to robust predictions. However, the assumptions necessary for causal inferen...
• Using Total Margin of Error to Account for Non-Sampling Error in Election Polls AI翻译
  作者：Dominitz, Jeff; Manski, Charles F.
  作者单位：Rice University; Northwestern University; Northwestern University
  摘要：The potential impact of non-sampling errors on election polls is well known, but measurement has focused on the margin of sampling error. Statisticians have recommended measurement of total survey error by mean square error (MSE), which jointly measures sampling and non-sampling errors. We suggest use of the square root of maximum MSE to measure the total margin of error (TME). We suggest that measurement of TME should be a standard feature in the reporting of polls. Because the exceedingly lo...
• Long-Term Effect Estimation When Combining Clinical Trial and Observational Follow-Up Datasets AI翻译
  作者：Cheng, Gang; Chen, Yen-Chi; Unger, Joseph M.; Till, Cathee; Zhao, Ying-Qi
  作者单位：University of Washington; University of Washington Seattle; Fred Hutchinson Cancer Center
  摘要：Combining experimental and observational follow-up datasets has received much attention lately. In a survival setting, recent work has used Medicare claims to extend the follow-up period for participants in a prostate cancer clinical trial. This allows the estimation of the long-term effect that cannot be estimated by the trial data alone. In this article, we study the estimation of long-term effect when participants in a clinical trial are linked to an observational follow-up dataset. Such li...
• Reinforcement Learning with Continuous Actions Under Unmeasured Confounding AI翻译
  作者：Li, Yuhan; Han, Eugene; Hu, Yifan; Zhou, Wenzhuo; Qi, Zhengling; Cui, Yifan; Zhu, Ruoqing
  作者单位：University of Illinois System; University of Illinois Urbana-Champaign; University of Illinois System; University of Illinois Urbana-Champaign; University of California System; University of California Irvine; George Washington University; Zhejiang University; Zhejiang University
  摘要：This article addresses the challenge of offline policy learning in continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially observable Markov decision processes (POMDPs) and assumes discrete action spaces, we advance this field by establishing a novel identification result to enable the nonparametric estimation of policy value for a given target policy under an infinite-horizon framework. Leveraging this identi...
• Toward Interpretable Deep Generative Models via Causal Representation Learning AI翻译
  作者：Moran, Gemma; Aragam, Bryon
  作者单位：Rutgers University System; Rutgers University New Brunswick; University of Chicago
  摘要：Recent developments in generative artificial intelligence (AI) rely on machine learning techniques such as deep learning and generative modeling to achieve state-of-the-art performance across wide-ranging domains. These methods' surprising performance is due in part to their ability to learn implicit representations of complex, multi-modal data. Unfortunately, deep neural networks are notoriously black boxes that obscure these representations, making them difficult to interpret or analyze. To ...
• Integrated Path Stability Selection AI翻译
  作者：Melikechi, Omar; Miller, Jeffrey W.
  作者单位：Harvard University; Harvard T.H. Chan School of Public Health
  摘要：Stability selection is a popular method for improving feature selection algorithms. One of its key attributes is that it provides theoretical upper bounds on the expected number of false positives, E(FP), enabling false positive control in practice. However, stability selection often selects few features because existing bounds on E(FP) are relatively loose. In this article, we introduce a novel approach to stability selection based on integrating stability paths rather than maximizing over th...
• Spatial Variation on Multiple Scales in Line Transect Data; the Case of Antarctic Fin Whales AI翻译
  作者：Breivik, Olav Nikolai; Skaug, Hans J.; Jullum, Martin; Biuw, Martin
  作者单位：University of Bergen; Institute of Marine Research - Norway; Institute of Marine Research - Norway
  摘要：Line transect sampling is a widely used survey method for estimating animal density or abundance. We present a novel model for such data that allows for spatial variation in animal density at two scales: a long scale, representing trends caused by for instance climatic or terrain gradients, and a short scale, representing abrupt shifts due to local effects such as prey patchiness. The long-range variation is modeled as a latent Gaussian random field, while the abrupt changes are modeled as a t...