The Model-free Prediction Principle has been successfully applied to general regression problems, as well as problems involving stationary and locally stationary time series. In this paper we demonstrate how Model-Free Prediction can be applied to handle random fields that are only locally stationary, i.e., they can be assumed to be stationary only across a limited part over their entire region of definition. We construct one-step-ahead point predictors and compare the performance of Model-free to Model-based prediction using models that incorporate a trend and/or heteroscedasticity. Both aspects of the paper, Model-free and Model-based, are novel in the context of random fields that are locally (but not globally) stationary. We demonstrate the application of our Model-based and Model-free point prediction methods to synthetic data as well as images from the CIFAR-10 dataset and in the latter case show that our best Model-free point prediction results outperform those obtained using Model-based prediction.
相關內容
This paper presents a new interaction point process that integrates geological knowledge for the purpose of automatic sources detection of multiple sources in groundwaters from hydrochemical data. The observations are considered as spatial data, that is a point cloud in a multi-dimensional space of hydrogeochemical parameters. The key hypothesis of this approach is to assume the unknown sources to be the realisation of a point process. The probability density describing the sources distribution is built in order to take into account the multi-dimensional character of the data and specific physical rules. These rules induce a source configuration able to explain the observations. This distribution is completed with prior knowledge regarding the model parameters distributions. The composition of the sources is estimated by the configuration maximising the joint proposed probability density. The method was first calibrated on synthetic data and then tested on real data from hydrothermal systems.
Generalized correlation analysis (GCA) is concerned with uncovering linear relationships across multiple datasets. It generalizes canonical correlation analysis that is designed for two datasets. We study sparse GCA when there are potentially multiple generalized correlation tuples in data and the loading matrix has a small number of nonzero rows. It includes sparse CCA and sparse PCA of correlation matrices as special cases. We first formulate sparse GCA as generalized eigenvalue problems at both population and sample levels via a careful choice of normalization constraints. Based on a Lagrangian form of the sample optimization problem, we propose a thresholded gradient descent algorithm for estimating GCA loading vectors and matrices in high dimensions. We derive tight estimation error bounds for estimators generated by the algorithm with proper initialization. We also demonstrate the prowess of the algorithm on a number of synthetic datasets.
The \emph{maximal $k$-edge-connected subgraphs} problem is a classical graph clustering problem studied since the 70's. Surprisingly, no non-trivial technique for this problem in weighted graphs is known: a very straightforward recursive-mincut algorithm with $\Omega(mn)$ time has remained the fastest algorithm until now. All previous progress gives a speed-up only when the graph is unweighted, and $k$ is small enough (e.g.~Henzinger~et~al.~(ICALP'15), Chechik~et~al.~(SODA'17), and Forster~et~al.~(SODA'20)). We give the first algorithm that breaks through the long-standing $\tilde{O}(mn)$-time barrier in \emph{weighted undirected} graphs. More specifically, we show a maximal $k$-edge-connected subgraphs algorithm that takes only $\tilde{O}(m\cdot\min\{m^{3/4},n^{4/5}\})$ time. As an immediate application, we can $(1+\epsilon)$-approximate the \emph{strength} of all edges in undirected graphs in the same running time. Our key technique is the first local cut algorithm with \emph{exact} cut-value guarantees whose running time depends only on the output size. All previous local cut algorithms either have running time depending on the cut value of the output, which can be arbitrarily slow in weighted graphs or have approximate cut guarantees.
Achieving highly accurate dynamic or simulator models that are close to the real robot can facilitate model-based controls (e.g., model predictive control or linear-quadradic regulators), model-based trajectory planning (e.g., trajectory optimization), and decrease the amount of learning time necessary for reinforcement learning methods. Thus, the objective of this work is to learn the residual errors between a dynamic and/or simulator model and the real robot. This is achieved using a neural network, where the parameters of a neural network are updated through an Unscented Kalman Filter (UKF) formulation. Using this method, we model these residual errors with only small amounts of data -- a necessity as we improve the simulator/dynamic model by learning directly from real-world operation. We demonstrate our method on robotic hardware (e.g., manipulator arm, and a wheeled robot), and show that with the learned residual errors, we can further close the reality gap between dynamic models, simulations, and actual hardware.
The ability to interpret machine learning models has become increasingly important as their usage in data science continues to rise. Most current interpretability methods are optimized to work on either (\textit{i}) a global scale, where the goal is to rank features based on their contributions to overall variation in an observed population, or (\textit{ii}) the local level, which aims to detail on how important a feature is to a particular individual in the dataset. In this work, we present the ``GlObal And Local Score'' (GOALS) operator: a simple \textit{post hoc} approach to simultaneously assess local and global feature variable importance in nonlinear models. Motivated by problems in statistical genetics, we demonstrate our approach using Gaussian process regression where understanding how genetic markers affect trait architecture both among individuals and across populations is of high interest. With detailed simulations and real data analyses, we illustrate the flexible and efficient utility of GOALS over state-of-the-art variable importance strategies.
Display Ads and the generalized assignment problem are two well-studied online packing problems with important applications in ad allocation and other areas. In both problems, ad impressions arrive online and have to be allocated immediately to budget-constrained advertisers. Worst-case algorithms that achieve the ideal competitive ratio are known, but might act overly conservative given the predictable and usually tame nature of real-world input. Given this discrepancy, we develop an algorithm for both problems that incorporate machine-learned predictions and can thus improve the performance beyond the worst-case. Our algorithm is based on the work of Feldman et al. (2009) and similar in nature to Mahdian et al. (2007) who were the first to develop a learning-augmented algorithm for the related, but more structured Ad Words problem. We use a novel analysis to show that our algorithm is able to capitalize on a good prediction, while being robust against poor predictions. We experimentally evaluate our algorithm on synthetic and real-world data on a wide range of predictions. Our algorithm is consistently outperforming the worst-case algorithm without predictions.
Online social media platforms offer access to a vast amount of information, but sifting through the abundance of news can be overwhelming and tiring for readers. personalised recommendation algorithms can help users find information that interests them. However, most existing models rely solely on observations of user behaviour, such as viewing history, ignoring the connections between the news and a user's prior knowledge. This can result in a lack of diverse recommendations for individuals. In this paper, we propose a novel method to address the complex problem of news recommendation. Our approach is based on the idea of dual observation, which involves using a deep neural network with observation mechanisms to identify the main focus of a news article as well as the focus of the user on the article. This is achieved by taking into account the user's belief network, which reflects their personal interests and biases. By considering both the content of the news and the user's perspective, our approach is able to provide more personalised and accurate recommendations. We evaluate the performance of our model on real-world datasets and show that our proposed method outperforms several popular baselines.
We present an end-to-end binaural impulse response generator (BIR) to generate plausible sounds in real-time for real-world models. Our approach uses a novel neural-network-based BIR generator (Scene2BIR) for the reconstructed 3D model. We propose a graph neural network that uses both the material and the topology information of the 3D scenes and generates a scene latent vector. Moreover, we use a conditional generative adversarial network (CGAN) to generate BIRs from the scene latent vector. Our network is able to handle holes or other artifacts in the reconstructed 3D mesh model. We present an efficient cost function to the generator network to incorporate spatial audio effects. Given the source and the listener position, our approach can generate a BIR in 0.1 milliseconds on an NVIDIA GeForce RTX 2080 Ti GPU and can easily handle multiple sources. We have evaluated the accuracy of our approach with real-world captured BIRs and an interactive geometric sound propagation algorithm.
The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN) based models generate richer and more expressive feature embeddings and hence also perform well on relation prediction. However, we observe that these KG embeddings treat triples independently and thus fail to cover the complex and hidden information that is inherently implicit in the local neighborhood surrounding a triple. To this effect, our paper proposes a novel attention based feature embedding that captures both entity and relation features in any given entity's neighborhood. Additionally, we also encapsulate relation clusters and multihop relations in our model. Our empirical study offers insights into the efficacy of our attention based model and we show marked performance gains in comparison to state of the art methods on all datasets.
With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). Existing solutions typically adopt class re-balancing strategies such as re-sampling and re-weighting based on the number of observations for each class. In this work, we argue that as the number of samples increases, the additional benefit of a newly added data point will diminish. We introduce a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point. The effective number of samples is defined as the volume of samples and can be calculated by a simple formula $(1-\beta^{n})/(1-\beta)$, where $n$ is the number of samples and $\beta \in [0,1)$ is a hyperparameter. We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss. Comprehensive experiments are conducted on artificially induced long-tailed CIFAR datasets and large-scale datasets including ImageNet and iNaturalist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191