Inference by means of mathematical modeling from a collection of observations remains a crucial tool for scientific discovery and is ubiquitous in application areas such as signal compression, imaging restoration, and supervised machine learning. The inference problems may be solved using variational formulations that provide theoretically proven methods and algorithms. With ever-increasing model complexities and growing data size, new specially designed methods are urgently needed to recover meaningful quantifies of interest. We consider the broad spectrum of linear inverse problems where the aim is to reconstruct quantities with a sparse representation on some vector space; often solved using the (generalized) least absolute shrinkage and selection operator (lasso). The associated optimization problems have received significant attention, in particular in the early 2000's, because of their connection to compressed sensing and the reconstruction of solutions with favorable sparsity properties using augmented Lagrangians, alternating directions and splitting methods. We provide a new perspective on the underlying l1 regularized inverse problem by exploring the generalized lasso problem through variable projection methods. We arrive at our proposed variable projected augmented Lagrangian (vpal) method. We analyze this method and provide an approach for automatic regularization parameter selection based on a degrees of freedom argument. Further, we provide numerical examples demonstrating the computational efficiency for various imaging problems.
相關內容
A new type of experiment that aims to determine the optimal quantities of a sequence of factors is eliciting considerable attention in medical science, bioengineering, and many other disciplines. Such studies require the simultaneous optimization of both quantities and the sequence orders of several components which are called quantitative-sequence (QS) factors. Given the large and semi-discrete solution spaces in such experiments, efficiently identifying optimal or near-optimal solutions by using a small number of experimental trials is a nontrivial task. To address this challenge, we propose a novel active learning approach, called QS-learning, to enable effective modeling and efficient optimization for experiments with QS factors. QS-learning consists of three parts: a novel mapping-based additive Gaussian process (MaGP) model, an efficient global optimization scheme (QS-EGO), and a new class of optimal designs (QS-design). The theoretical properties of the proposed method are investigated, and optimization techniques using analytical gradients are developed. The performance of the proposed method is demonstrated via a real drug experiment on lymphoma treatment and several simulation studies.
The growing availability of observational databases like electronic health records (EHR) provides unprecedented opportunities for secondary use of such data in biomedical research. However, these data can be error-prone and need to be validated before use. It is usually unrealistic to validate the whole database due to resource constraints. A cost-effective alternative is to implement a two-phase design that validates a subset of patient records that are enriched for information about the research question of interest. Herein, we consider odds ratio estimation under differential outcome and exposure misclassification. We propose optimal designs that minimize the variance of the maximum likelihood odds ratio estimator. We develop a novel adaptive grid search algorithm that can locate the optimal design in a computationally feasible and numerically accurate manner. Because the optimal design requires specification of unknown parameters at the outset and thus is unattainable without prior information, we introduce a multi-wave sampling strategy to approximate it in practice. We demonstrate the efficiency gains of the proposed designs over existing ones through extensive simulations and two large observational studies. We provide an R package and Shiny app to facilitate the use of the optimal designs.
In this work, we study the convergence and performance of nonlinear solvers for the Bidomain equations after decoupling the ordinary and partial differential equations of the cardiac system. We first rigorously prove that Quasi-Newton methods such as BFGS and nonlinear Conjugate-Gradient such as Fletcher-Reeves methods are globally convergent, by studying an auxiliary variational problem under physically reasonable hypotheses. Then, we compare several nonlinear solvers in terms of execution time, robustness with respect to the data and parallel scalability. Our results suggest that Quasi-Newton methods are the best choice for this type of problem, being faster than standard Newton-Krylov methods without hindering their robustness or scalability. In addition, first order methods are also competitive, and represent a better alternative for matrix-free implementations, which are suitable for GPU computing.
We perform a posteriori error analysis in the supremum norm for the quadratic discontinuous Galerkin method for the elliptic obstacle problem. We define two discrete sets (motivated by Gaddam, Gudi and Kamana [1]), one set having integral constraints and other one with the nodal constraints at the quadrature points, and discuss the pointwise reliability and efficiency of the proposed a posteriori error estimator. In the analysis, we employ a linear averaging function to transfer DG finite element space to standard conforming finite element space and exploit the sharp bounds on the Green's function of the Poisson's problem. Moreover, the upper and the lower barrier functions corresponding to continuous solution u are constructed by modifying the conforming part of the discrete solution uh appropriately. Finally, numerical experiments are presented to complement the theoretical results.
The stochastic partial differential equation (SPDE) approach is widely used for modeling large spatial datasets. It is based on representing a Gaussian random field $u$ on $\mathbb{R}^d$ as the solution of an elliptic SPDE $L^\beta u = \mathcal{W}$ where $L$ is a second-order differential operator, $2\beta$ (belongs to natural number starting from 1) is a positive parameter that controls the smoothness of $u$ and $\mathcal{W}$ is Gaussian white noise. A few approaches have been suggested in the literature to extend the approach to allow for any smoothness parameter satisfying $\beta>d/4$. Even though those approaches work well for simulating SPDEs with general smoothness, they are less suitable for Bayesian inference since they do not provide approximations which are Gaussian Markov random fields (GMRFs) as in the original SPDE approach. We address this issue by proposing a new method based on approximating the covariance operator $L^{-2\beta}$ of the Gaussian field $u$ by a finite element method combined with a rational approximation of the fractional power. This results in a numerically stable GMRF approximation which can be combined with the integrated nested Laplace approximation (INLA) method for fast Bayesian inference. A rigorous convergence analysis of the method is performed and the accuracy of the method is investigated with simulated data. Finally, we illustrate the approach and corresponding implementation in the R package rSPDE via an application to precipitation data which is analyzed by combining the rSPDE package with the R-INLA software for full Bayesian inference.
Mixture models are widely used to fit complex and multimodal datasets. In this paper we study mixtures with high dimensional sparse latent parameter vectors and consider the problem of support recovery of those vectors. While parameter learning in mixture models is well-studied, the sparsity constraint remains relatively unexplored. Sparsity of parameter vectors is a natural constraint in variety of settings, and support recovery is a major step towards parameter estimation. We provide efficient algorithms for support recovery that have a logarithmic sample complexity dependence on the dimensionality of the latent space. Our algorithms are quite general, namely they are applicable to 1) mixtures of many different canonical distributions including Uniform, Poisson, Laplace, Gaussians, etc. 2) Mixtures of linear regressions and linear classifiers with Gaussian covariates under different assumptions on the unknown parameters. In most of these settings, our results are the first guarantees on the problem while in the rest, our results provide improvements on existing works.
In explainable machine learning, local post-hoc explanation algorithms and inherently interpretable models are often seen as competing approaches. In this work, offer a novel perspective on Shapley Values, a prominent post-hoc explanation technique, and show that it is strongly connected with Glassbox-GAMs, a popular class of interpretable models. We introduce $n$-Shapley Values, a natural extension of Shapley Values that explain individual predictions with interaction terms up to order $n$. As $n$ increases, the $n$-Shapley Values converge towards the Shapley-GAM, a uniquely determined decomposition of the original function. From the Shapley-GAM, we can compute Shapley Values of arbitrary order, which gives precise insights into the limitations of these explanations. We then show that Shapley Values recover generalized additive models of order $n$, assuming that we allow for interaction terms up to order $n$ in the explanations. This implies that the original Shapley Values recover Glassbox-GAMs. At the technical end, we show that there is a one-to-one correspondence between different ways to choose the value function and different functional decompositions of the original function. This provides a novel perspective on the question of how to choose the value function. We also present an empirical analysis of the degree of variable interaction that is present in various standard classifiers, and discuss the implications of our results for algorithmic explanations. A python package to compute $n$-Shapley Values and replicate the results in this paper is available at \url{//github.com/tml-tuebingen/nshap}.
Alzheimer's disease (AD), as a progressive brain disease, affects cognition, memory, and behavior. Similarly, limbic-predominant age-related TDP-43 encephalopathy (LATE) is a recently defined common neurodegenerative disease that mimics the clinical symptoms of AD. At present, the risk factors implicated in LATE and those distinguishing LATE from AD are largely unknown. We leveraged an integrated feature selection-based algorithmic approach, to identify important factors differentiating subjects with LATE and/or AD from Control on significantly imbalanced data. We analyzed two datasets ROSMAP and NACC and discovered that alcohol consumption was a top lifestyle and environmental factor linked with LATE and AD and their associations were differential. In particular, we identified a specific subpopulation consisting of APOE e4 carriers. We found that, for this subpopulation, light-to-moderate alcohol intake was a protective factor against both AD and LATE, but its protective role against AD appeared stronger than LATE. The codes for our algorithms are available at //github.com/xinxingwu-uk/PFV.
Graph neural networks generalize conventional neural networks to graph-structured data and have received widespread attention due to their impressive representation ability. In spite of the remarkable achievements, the performance of Euclidean models in graph-related learning is still bounded and limited by the representation ability of Euclidean geometry, especially for datasets with highly non-Euclidean latent anatomy. Recently, hyperbolic space has gained increasing popularity in processing graph data with tree-like structure and power-law distribution, owing to its exponential growth property. In this survey, we comprehensively revisit the technical details of the current hyperbolic graph neural networks, unifying them into a general framework and summarizing the variants of each component. More importantly, we present various HGNN-related applications. Last, we also identify several challenges, which potentially serve as guidelines for further flourishing the achievements of graph learning in hyperbolic spaces.
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.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191