We present a methodology based on filtered data and moving averages for estimating robustly effective dynamics from observations of multiscale systems. We show in a semi-parametric framework of the Langevin type that the method we propose is asymptotically unbiased with respect to homogenization theory. Moreover, we demonstrate with a series of numerical experiments that the method we propose here outperforms traditional techniques for extracting coarse-grained dynamics from data, such as subsampling, in terms of bias and of robustness.
相關內容
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i.e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence. The existing approaches to RefVSR essentially attempt to align the reference and the input sequence, in the presence of resolution gap and long temporal range. However, they either ignore temporal structure within the input sequence, or suffer accumulative alignment errors. To address these issues, we propose EFENet to exploit simultaneously the visual cues contained in the HR reference and the temporal information contained in the LR sequence. EFENet first globally estimates cross-scale flow between the reference and each LR frame. Then our novel flow refinement module of EFENet refines the flow regarding the furthest frame using all the estimated flows, which leverages the global temporal information within the sequence and therefore effectively reduces the alignment errors. We provide comprehensive evaluations to validate the strengths of our approach, and to demonstrate that the proposed framework outperforms the state-of-the-art methods. Code is available at //github.com/IndigoPurple/EFENet.
There is an intimate connection between numerical upscaling of multiscale PDEs and scattered data approximation of heterogeneous functions: the coarse variables selected for deriving an upscaled equation (in the former) correspond to the sampled information used for approximation (in the latter). As such, both problems can be thought of as recovering a target function based on some coarse data that are either artificially chosen by an upscaling algorithm, or determined by some physical measurement process. The purpose of this paper is then to study that, under such a setup and for a specific elliptic problem, how the lengthscale of the coarse data, which we refer to as the subsampled lengthscale, influences the accuracy of recovery, given limited computational budgets. Our analysis and experiments identify that, reducing the subsampling lengthscale may improve the accuracy, implying a guiding criterion for coarse-graining or data acquisition in this computationally constrained scenario, especially leading to direct insights for the implementation of the Gamblets method in the numerical homogenization literature. Moreover, reducing the lengthscale to zero may lead to a blow-up of approximation error if the target function does not have enough regularity, suggesting the need for a stronger prior assumption on the target function to be approximated. We introduce a singular weight function to deal with it, both theoretically and numerically. This work sheds light on the interplay of the lengthscale of coarse data, the computational costs, the regularity of the target function, and the accuracy of approximations and numerical simulations.
We propose, analyze, and test a novel continuous data assimilation two-phase flow algorithm for reservoir simulation. We show that the solutions of the algorithm, constructed using coarse mesh observations, converge at an exponential rate in time to the corresponding exact reference solution of the two-phase model. More precisely, we obtain a stability estimate which illustrates an exponential decay of the residual error between the reference and approximate solution, until the error hits a threshold depending on the order of data resolution. Numerical computations are included to demonstrate the effectiveness of this approach, as well as variants with data on sub-domains. In particular, we demonstrate numerically that synchronization is achieved for data collected from a small fraction of the domain.
We investigate the issue of parameter estimation with nonuniform negative sampling for imbalanced data. We first prove that, with imbalanced data, the available information about unknown parameters is only tied to the relatively small number of positive instances, which justifies the usage of negative sampling. However, if the negative instances are subsampled to the same level of the positive cases, there is information loss. To maintain more information, we derive the asymptotic distribution of a general inverse probability weighted (IPW) estimator and obtain the optimal sampling probability that minimizes its variance. To further improve the estimation efficiency over the IPW method, we propose a likelihood-based estimator by correcting log odds for the sampled data and prove that the improved estimator has the smallest asymptotic variance among a large class of estimators. It is also more robust to pilot misspecification. We validate our approach on simulated data as well as a real click-through rate dataset with more than 0.3 trillion instances, collected over a period of a month. Both theoretical and empirical results demonstrate the effectiveness of our method.
Functional Principal Component Analysis is a reference method for dimension reduction of curve data. Its theoretical properties are now well understood in the simplified case where the sample curves are fully observed without noise. However, functional data are noisy and necessarily observed on a finite discretization grid. Common practice consists in smoothing the data and then to compute the functional estimates, but the impact of this denoising step on the procedure's statistical performance are rarely considered. Here we prove new convergence rates for functional principal component estimators. We introduce a double asymptotic framework: one corresponding to the sampling size and a second to the size of the grid. We prove that estimates based on projection onto histograms show optimal rates in a minimax sense. Theoretical results are illustrated on simulated data and the method is applied to the visualization of genomic data.
In this paper, we propose an offline-online strategy based on the Localized Orthogonal Decomposition (LOD) method for elliptic multiscale problems with randomly perturbed diffusion coefficient. We consider a periodic deterministic coefficient with local defects that occur with probability $p$. The offline phase pre-computes entries to global LOD stiffness matrices on a single reference element (exploiting the periodicity) for a selection of defect configurations. Given a sample of the perturbed diffusion the corresponding LOD stiffness matrix is then computed by taking linear combinations of the pre-computed entries, in the online phase. Our computable error estimates show that this yields a good coarse-scale approximation of the solution for small $p$, which is illustrated by extensive numerical experiments. This makes the proposed technique attractive already for moderate sample sizes in a Monte Carlo simulation.
Imbalanced data occurs in a wide range of scenarios. The skewed distribution of the target variable elicits bias in machine learning algorithms. One of the popular methods to combat imbalanced data is to artificially balance the data through resampling. In this paper, we compare the efficacy of a recently proposed kernel density estimation (KDE) sampling technique in the context of artificial neural networks. We benchmark the KDE sampling method against two base sampling techniques and perform comparative experiments using 8 datasets and 3 neural networks architectures. The results show that KDE sampling produces the best performance on 6 out of 8 datasets. However, it must be used with caution on image datasets. We conclude that KDE sampling is capable of significantly improving the performance of neural networks.
We consider the use of deep learning for parameter estimation. We propose Bias Constrained Estimators (BCE) that add a squared bias term to the standard mean squared error (MSE) loss. The main motivation to BCE is learning to estimate deterministic unknown parameters with no Bayesian prior. Unlike standard learning based estimators that are optimal on average, we prove that BCEs converge to Minimum Variance Unbiased Estimators (MVUEs). We derive closed form solutions to linear BCEs. These provide a flexible bridge between linear regrssion and the least squares method. In non-linear settings, we demonstrate that BCEs perform similarly to MVUEs even when the latter are computationally intractable. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance. Examples include distributed sensor networks and data augmentation in test-time. In such applications, unbiasedness is a necessary condition for asymptotic consistency.
The reach of a set $M \subset \mathbb R^d$, also known as condition number when $M$ is a manifold, was introduced by Federer in 1959 and is a central concept in geometric measure theory, set estimation, manifold learning, among others areas. We introduce a universally consistent estimate of the reach, just assuming that the reach is positive. A necessary condition for the universal convergence of the reach is that the Haussdorf distance between the sample and the set converges to zero. Without further assumptions we show that the convergence rate of this distance can be arbitrarily slow. However, under a weak additional assumption, we provide rates of convergence for the reach estimator. We also show that it is not possible to determine if the reach of the support of a density is zero or not based on a finite sample. We provide a small simulation study and a bias correction method for the case when $M$ is a manifold.
Heatmap-based methods dominate in the field of human pose estimation by modelling the output distribution through likelihood heatmaps. In contrast, regression-based methods are more efficient but suffer from inferior performance. In this work, we explore maximum likelihood estimation (MLE) to develop an efficient and effective regression-based methods. From the perspective of MLE, adopting different regression losses is making different assumptions about the output density function. A density function closer to the true distribution leads to a better regression performance. In light of this, we propose a novel regression paradigm with Residual Log-likelihood Estimation (RLE) to capture the underlying output distribution. Concretely, RLE learns the change of the distribution instead of the unreferenced underlying distribution to facilitate the training process. With the proposed reparameterization design, our method is compatible with off-the-shelf flow models. The proposed method is effective, efficient and flexible. We show its potential in various human pose estimation tasks with comprehensive experiments. Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead. Moreover, for the first time, especially on multi-person pose estimation, our regression method is superior to the heatmap-based methods. Our code is available at //github.com/Jeff-sjtu/res-loglikelihood-regression
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