The recent proliferation of medical data, such as genetics and electronic health records (EHR), offers new opportunities to find novel predictors of health outcomes. Presented with a large set of candidate features, interest often lies in selecting the ones most likely to be predictive of an outcome for further study such that the goal is to control the false discovery rate (FDR) at a specified level. Knockoff filtering is an innovative strategy for FDR-controlled feature selection. But, existing knockoff methods make strong distributional assumptions that hinder their applicability to real world data. We propose Bayesian models for generating high quality knockoff copies that utilize available knowledge about the data structure, thus improving the resolution of prognostic features. Applications to two feature sets are considered: those with categorical and/or continuous variables possibly having a population substructure, such as in EHR; and those with microbiome features having a compositional constraint and phylogenetic relatedness. Through simulations and real data applications, these methods are shown to identify important features with good FDR control and power.
相關內容
We construct a zig-zag process targeting a posterior distribution defined on a hybrid state space consisting of both discrete and continuous variables. The construction does not require any assumptions on the structure among discrete variables. We demonstrate our method on two examples in genetics based on the Kingman coalescent, showing that the zig-zag process can lead to efficiency gains of up to several orders of magnitude over classical Metropolis-Hastings algorithms, and that it is well suited to parallel computation. Our construction resembles existing techniques for Hamiltonian Monte Carlo on a hybrid state space, which suffers from implementationally and analytically complex boundary crossings when applied to the coalescent. We demonstrate that the continuous-time zig-zag process avoids these complications.
Image reconstruction based on indirect, noisy, or incomplete data remains an important yet challenging task. While methods such as compressive sensing have demonstrated high-resolution image recovery in various settings, there remain issues of robustness due to parameter tuning. Moreover, since the recovery is limited to a point estimate, it is impossible to quantify the uncertainty, which is often desirable. Due to these inherent limitations, a sparse Bayesian learning approach is sometimes adopted to recover a posterior distribution of the unknown. Sparse Bayesian learning assumes that some linear transformation of the unknown is sparse. However, most of the methods developed are tailored to specific problems, with particular forward models and priors. Here, we present a generalized approach to sparse Bayesian learning. It has the advantage that it can be used for various types of data acquisitions and prior information. Some preliminary results on image reconstruction/recovery indicate its potential use for denoising, deblurring, and magnetic resonance imaging.
Data and Science has stood out in the generation of results, whether in the projects of the scientific domain or business domain. CERN Project, Scientific Institutes, companies like Walmart, Google, Apple, among others, need data to present their results and make predictions in the competitive data world. Data and Science are words that together culminated in a globally recognized term called Data Science. Data Science is in its initial phase, possibly being part of formal sciences and also being presented as part of applied sciences, capable of generating value and supporting decision making. Data Science considers science and, consequently, the scientific method to promote decision making through data intelligence. In many cases, the application of the method (or part of it) is considered in Data Science projects in scientific domain (social sciences, bioinformatics, geospatial projects) or business domain (finance, logistic, retail), among others. In this sense, this article addresses the perspectives of Data Science as a multidisciplinary area, considering science and the scientific method, and its formal structure which integrate Statistics, Computer Science, and Business Science, also taking into account Artificial Intelligence, emphasizing Machine Learning, among others. The article also deals with the perspective of applied Data Science, since Data Science is used for generating value through scientific and business projects. Data Science persona is also discussed in the article, concerning the education of Data Science professionals and its corresponding profiles, since its projection changes the field of data in the world.
Analytics corresponds to a relevant and challenging phase of Big Data. The generation of knowledge from extensive data sets (petabyte era) of varying types, occurring at a speed able to serve decision makers, is practiced using multiple areas of knowledge, such as computing, statistics, data mining, among others. In the Big Data domain, Analytics is also considered as a process capable of adding value to the organizations. Besides the demonstration of value, Analytics should also consider operational tools and models to support decision making. To adding value, Analytics is also presented as part of some Big Data value chains, such the Information Value Chain presented by NIST among others, which are detailed in this article. As well, some maturity models are presented, since they represent important structures to favor continuous implementation of Analytics for Big Data, using specific technologies, techniques and methods. Hence, through an in-depth research, using specific literature references and use cases, we seeks to outline an approach to determine the Analytical Engineering for Big Data Analytics considering four pillars: Data, Models, Tools and People; and three process groups: Acquisition, Retention and Revision; in order to make feasible and to define an organization, possibly designated as an Analytics Organization, responsible for generating knowledge from the data in the field of Big Data Analytics.
Much of the micro data used for epidemiological studies contain sensitive measurements on real individuals. As a result, such micro data cannot be published out of privacy concerns, rendering any published statistical analyses on them nearly impossible to reproduce. To promote the dissemination of key datasets for analysis without jeopardizing the privacy of individuals, we introduce a cohesive Bayesian framework for the generation of fully synthetic, high dimensional micro datasets of mixed categorical, binary, count, and continuous variables. This process centers around a joint Bayesian model that is simultaneously compatible with all of these data types, enabling the creation of mixed synthetic datasets through posterior predictive sampling. Furthermore, a focal point of epidemiological data analysis is the study of conditional relationships between various exposures and key outcome variables through regression analysis. We design a modified data synthesis strategy to target and preserve these conditional relationships, including both nonlinearities and interactions. The proposed techniques are deployed to create a synthetic version of a confidential dataset containing dozens of health, cognitive, and social measurements on nearly 20,000 North Carolina children.
This PhD thesis contains several contributions to the field of statistical causal modeling. Statistical causal models are statistical models embedded with causal assumptions that allow for the inference and reasoning about the behavior of stochastic systems affected by external manipulation (interventions). This thesis contributes to the research areas concerning the estimation of causal effects, causal structure learning, and distributionally robust (out-of-distribution generalizing) prediction methods. We present novel and consistent linear and non-linear causal effects estimators in instrumental variable settings that employ data-dependent mean squared prediction error regularization. Our proposed estimators show, in certain settings, mean squared error improvements compared to both canonical and state-of-the-art estimators. We show that recent research on distributionally robust prediction methods has connections to well-studied estimators from econometrics. This connection leads us to prove that general K-class estimators possess distributional robustness properties. We, furthermore, propose a general framework for distributional robustness with respect to intervention-induced distributions. In this framework, we derive sufficient conditions for the identifiability of distributionally robust prediction methods and present impossibility results that show the necessity of several of these conditions. We present a new structure learning method applicable in additive noise models with directed trees as causal graphs. We prove consistency in a vanishing identifiability setup and provide a method for testing substructure hypotheses with asymptotic family-wise error control that remains valid post-selection. Finally, we present heuristic ideas for learning summary graphs of nonlinear time-series models.
This paper seeks to develop a deeper understanding of the fundamental properties of neural text generations models. The study of artifacts that emerge in machine generated text as a result of modeling choices is a nascent research area. Previously, the extent and degree to which these artifacts surface in generated text has not been well studied. In the spirit of better understanding generative text models and their artifacts, we propose the new task of distinguishing which of several variants of a given model generated a piece of text, and we conduct an extensive suite of diagnostic tests to observe whether modeling choices (e.g., sampling methods, top-$k$ probabilities, model architectures, etc.) leave detectable artifacts in the text they generate. Our key finding, which is backed by a rigorous set of experiments, is that such artifacts are present and that different modeling choices can be inferred by observing the generated text alone. This suggests that neural text generators may be more sensitive to various modeling choices than previously thought.
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
Graph neural networks (GNNs) are a popular class of machine learning models whose major advantage is their ability to incorporate a sparse and discrete dependency structure between data points. Unfortunately, GNNs can only be used when such a graph-structure is available. In practice, however, real-world graphs are often noisy and incomplete or might not be available at all. With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph. This allows one to apply GCNs not only in scenarios where the given graph is incomplete or corrupted but also in those where a graph is not available. We conduct a series of experiments that analyze the behavior of the proposed method and demonstrate that it outperforms related methods by a significant margin.
Steve Jobs, one of the greatest visionaries of our time was quoted in 1996 saying "a lot of times, people do not know what they want until you show it to them" [38] indicating he advocated products to be developed based on human intuition rather than research. With the advancements of mobile devices, social networks and the Internet of Things, enormous amounts of complex data, both structured and unstructured are being captured in hope to allow organizations to make better business decisions as data is now vital for an organizations success. These enormous amounts of data are referred to as Big Data, which enables a competitive advantage over rivals when processed and analyzed appropriately. However Big Data Analytics has a few concerns including Management of Data-lifecycle, Privacy & Security, and Data Representation. This paper reviews the fundamental concept of Big Data, the Data Storage domain, the MapReduce programming paradigm used in processing these large datasets, and focuses on two case studies showing the effectiveness of Big Data Analytics and presents how it could be of greater good in the future if handled appropriately.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191