亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

We consider the optimization of a smooth and strongly convex objective using constant step-size stochastic gradient descent (SGD) and study its properties through the prism of Markov chains. We show that, for unbiased gradient estimates with mildly controlled variance, the iteration converges to an invariant distribution in total variation distance. We also establish this convergence in Wasserstein-2 distance under a relaxed assumption on the gradient noise distribution compared to previous work. Thanks to the invariance property of the limit distribution, our analysis shows that the latter inherits sub-Gaussian or sub-exponential concentration properties when these hold true for the gradient. This allows the derivation of high-confidence bounds for the final estimate. Finally, under such conditions in the linear case, we obtain a dimension-free deviation bound for the Polyak-Ruppert average of a tail sequence. All our results are non-asymptotic and their consequences are discussed through a few applications.

In a task where many similar inverse problems must be solved, evaluating costly simulations is impractical. Therefore, replacing the model $y$ with a surrogate model $y_s$ that can be evaluated quickly leads to a significant speedup. The approximation quality of the surrogate model depends strongly on the number, position, and accuracy of the sample points. With an additional finite computational budget, this leads to a problem of (computer) experimental design. In contrast to the selection of sample points, the trade-off between accuracy and effort has hardly been studied systematically. We therefore propose an adaptive algorithm to find an optimal design in terms of position and accuracy. Pursuing a sequential design by incrementally appending the computational budget leads to a convex and constrained optimization problem. As a surrogate, we construct a Gaussian process regression model. We measure the global approximation error in terms of its impact on the accuracy of the identified parameter and aim for a uniform absolute tolerance, assuming that $y_s$ is computed by finite element calculations. A priori error estimates and a coarse estimate of computational effort relate the expected improvement of the surrogate model error to computational effort, resulting in the most efficient combination of sample point and evaluation tolerance. We also allow for improving the accuracy of already existing sample points by continuing previously truncated finite element solution procedures.

In this paper, we consider the interference rejection combining (IRC) receiver, which improves the cell-edge user throughput via suppressing inter-cell interference and requires estimating the covariance matrix including the inter-cell interference with high accuracy. In order to solve the problem of sample covariance matrix estimation with limited samples, a regularization parameter optimization based on the minimum eigenvalue criterion is developed. It is different from traditional methods that aim at minimizing the mean squared error, but goes straight at the objective of optimizing the final performance of the IRC receiver. A lower bound of the minimum eigenvalue that is easier to calculate is also derived. Simulation results demonstrate that the proposed approach is effective and can approach the performance of the oracle estimator in terms of the mutual information metric.

Stepped wedge cluster randomized experiments represent a class of unidirectional crossover designs that are increasingly adopted for comparative effectiveness and implementation science research. Although stepped wedge cluster randomized experiments have become popular, definitions of estimands and robust methods to target clearly-defined estimands remain insufficient. To address this gap, we describe a class of estimands that explicitly acknowledge the multilevel data structure in stepped wedge cluster randomized experiments, and highlight three typical members of the estimand class that are interpretable and are of practical interest. We then discuss four formulations of analysis of covariance (ANCOVA) working models to achieve estimand-aligned analyses. By exploiting baseline covariates, each ANCOVA model can potentially improve the estimation efficiency over the unadjusted estimators. In addition, each ANCOVA estimator is model-assisted in a sense that its point estimator is consistent to the target estimand even when the working model is misspecified. Under the stepped wedge randomization scheme, we establish the finite population Central Limit Theorem for each estimator, which motivates design-based variance estimators. Through simulations, we study the finite-sample operating characteristics of the ANCOVA estimators under different data generating processes. We illustrate their applications via the analysis of the Washington State Expedited Partner Therapy study.

The fundamental problem of weighted sampling involves sampling of satisfying assignments of Boolean formulas, which specify sampling sets, and according to distributions defined by pre-specified weight functions to weight functions. The tight integration of sampling routines in various applications has highlighted the need for samplers to be incremental, i.e., samplers are expected to handle updates to weight functions. The primary contribution of this work is an efficient knowledge compilation-based weighted sampler, INC, designed for incremental sampling. INC builds on top of the recently proposed knowledge compilation language, OBDD[AND], and is accompanied by rigorous theoretical guarantees. Our extensive experiments demonstrate that INC is faster than state-of-the-art approach for majority of the evaluation. In particular, we observed a median of 1.69X runtime improvement over the prior state-of-the-art approach.

Elliptical distribution is a basic assumption underlying many multivariate statistical methods. For example, in sufficient dimension reduction and statistical graphical models, this assumption is routinely imposed to simplify the data dependence structure. Before applying such methods, we need to decide whether the data are elliptically distributed. Currently existing tests either focus exclusively on spherical distributions, or rely on bootstrap to determine the null distribution, or require specific forms of the alternative distribution. In this paper, we introduce a general nonparametric test for elliptical distribution based on kernel embedding of the probability measure that embodies the two properties that characterize an elliptical distribution: namely, after centering and rescaling, (1) the direction and length of the random vector are independent, and (2) the directional vector is uniformly distributed on the unit sphere. We derive the null asymptotic distribution of the test statistic via von-Mises expansion, develop the sample-level procedure to determine the rejection region, and establish the consistency and validity of the proposed test. We apply our test to a SENIC dataset with and without a transformation aimed to achieve ellipticity.

This paper explores variants of the subspace iteration algorithm for computing approximate invariant subspaces. The standard subspace iteration approach is revisited and new variants that exploit gradient-type techniques combined with a Grassmann manifold viewpoint are developed. A gradient method as well as a conjugate gradient technique are described. Convergence of the gradient-based algorithm is analyzed and a few numerical experiments are reported, indicating that the proposed algorithms are sometimes superior to a standard Chebyshev-based subspace iteration when compared in terms of number of matrix vector products, but do not require estimating optimal parameters. An important contribution of this paper to achieve this good performance is the accurate and efficient implementation of an exact line search. In addition, new convergence proofs are presented for the non-accelerated gradient method that includes a locally exponential convergence if started in a $\mathcal{O(\sqrt{\delta})}$ neighbourhood of the dominant subspace with spectral gap $\delta$.

The Information Bottleneck (IB) is a method of lossy compression. Its rate-distortion (RD) curve describes the fundamental tradeoff between input compression and the preservation of relevant information. However, it conceals the underlying dynamics of optimal input encodings. We argue that these typically follow a piecewise smooth trajectory as the input information is being compressed, as recently shown in RD. These smooth dynamics are interrupted when an optimal encoding changes qualitatively, at a bifurcation. By leveraging the IB's intimate relations with RD, sub-optimal solutions can be seen to collide or exchange optimality there. Despite the acceptance of the IB and its applications, there are surprisingly few techniques to solve it numerically, even for finite problems whose distribution is known. We derive anew the IB's first-order Ordinary Differential Equation, which describes the dynamics underlying its optimal tradeoff curve. To exploit these dynamics, one needs not only to detect IB bifurcations but also to identify their type in order to handle them accordingly. Rather than approaching the optimal IB curve from sub-optimal directions, the latter allows us to follow a solution's trajectory along the optimal curve, under mild assumptions. Thereby, translating an understanding of IB bifurcations into a surprisingly accurate numerical algorithm.

Bayesian neural networks (BNNs) provide a formalism to quantify and calibrate uncertainty in deep learning. Current inference approaches for BNNs often resort to few-sample estimation for scalability, which can harm predictive performance, while its alternatives tend to be computationally prohibitively expensive. We tackle this challenge by revealing a previously unseen connection between inference on BNNs and volume computation problems. With this observation, we introduce a novel collapsed inference scheme that performs Bayesian model averaging using collapsed samples. It improves over a Monte-Carlo sample by limiting sampling to a subset of the network weights while pairing it with some closed-form conditional distribution over the rest. A collapsed sample represents uncountably many models drawn from the approximate posterior and thus yields higher sample efficiency. Further, we show that the marginalization of a collapsed sample can be solved analytically and efficiently despite the non-linearity of neural networks by leveraging existing volume computation solvers. Our proposed use of collapsed samples achieves a balance between scalability and accuracy. On various regression and classification tasks, our collapsed Bayesian deep learning approach demonstrates significant improvements over existing methods and sets a new state of the art in terms of uncertainty estimation as well as predictive performance.

It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the training bias. Despite the promising performances, super slow training is currently the bottleneck in the meta learning approaches. In this paper, we introduce a novel Faster Meta Update Strategy (FaMUS) to replace the most expensive step in the meta gradient computation with a faster layer-wise approximation. We empirically find that FaMUS yields not only a reasonably accurate but also a low-variance approximation of the meta gradient. We conduct extensive experiments to verify the proposed method on two tasks. We show our method is able to save two-thirds of the training time while still maintaining the comparable or achieving even better generalization performance. In particular, our method achieves the state-of-the-art performance on both synthetic and realistic noisy labels, and obtains promising performance on long-tailed recognition on standard benchmarks.