Most implementations of Bayesian additive regression trees (BART) one-hot encode categorical predictors, replacing each one with several binary indicators, one for every level or category. Regression trees built with these indicators partition the discrete set of categorical levels by repeatedly removing one level at a time. Unfortunately, the vast majority of partitions cannot be built with this strategy, severely limiting BART's ability to partially pool data across groups of levels. Motivated by analyses of baseball data and neighborhood-level crime dynamics, we overcame this limitation by re-implementing BART with regression trees that can assign multiple levels to both branches of a decision tree node. To model spatial data aggregated into small regions, we further proposed a new decision rule prior that creates spatially contiguous regions by deleting a random edge from a random spanning tree of a suitably defined network. Our re-implementation, which is available in the flexBART package, often yields improved out-of-sample predictive performance and scales better to larger datasets than existing implementations of BART.
相關內容
The approach to analysing compositional data has been dominated by the use of logratio transformations, to ensure exact subcompositional coherence and, in some situations, exact isometry as well. A problem with this approach is that data zeros, found in most applications, have to be replaced to allow the logarithmic transformation. An alternative new approach, called the `chiPower' transformation, which allows data zeros, is to combine the standardization inherent in the chi-square distance in correspondence analysis, with the essential elements of the Box-Cox power transformation. The chiPower transformation is justified because it} defines between-sample distances that tend to logratio distances for strictly positive data as the power parameter tends to zero, and are then equivalent to transforming to logratios. For data with zeros, a value of the power can be identified that brings the chiPower transformation as close as possible to a logratio transformation, without having to substitute the zeros. Especially in the area of high-dimensional data, this alternative approach can present such a high level of coherence and isometry as to be a valid approach to the analysis of compositional data. Furthermore, in a supervised learning context, if the compositional variables serve as predictors of a response in a modelling framework, for example generalized linear models, then the power can be used as a tuning parameter in optimizing the accuracy of prediction through cross-validation. The chiPower-transformed variables have a straightforward interpretation, since they are each identified with single compositional parts, not ratios.
Hyperspectral imagery contains abundant spectral information beyond the visible RGB bands, providing rich discriminative details about objects in a scene. Leveraging such data has the potential to enhance visual tracking performance. While prior hyperspectral trackers employ CNN or hybrid CNN-Transformer architectures, we propose a novel approach HPFormer on Transformers to capitalize on their powerful representation learning capabilities. The core of HPFormer is a Hyperspectral Hybrid Attention (HHA) module which unifies feature extraction and fusion within one component through token interactions. Additionally, a Transform Band Module (TBM) is introduced to selectively aggregate spatial details and spectral signatures from the full hyperspectral input for injecting informative target representations. Extensive experiments demonstrate state-of-the-art performance of HPFormer on benchmark NIR and VIS tracking datasets. Our work provides new insights into harnessing the strengths of transformers and hyperspectral fusion to advance robust object tracking.
LSM-trees are widely adopted as the storage backend of key-value stores. However, optimizing the system performance under dynamic workloads has not been sufficiently studied or evaluated in previous work. To fill the gap, we present RusKey, a key-value store with the following new features: (1) RusKey is a first attempt to orchestrate LSM-tree structures online to enable robust performance under the context of dynamic workloads; (2) RusKey is the first study to use Reinforcement Learning (RL) to guide LSM-tree transformations; (3) RusKey includes a new LSM-tree design, named FLSM-tree, for an efficient transition between different compaction policies -- the bottleneck of dynamic key-value stores. We justify the superiority of the new design with theoretical analysis; (4) RusKey requires no prior workload knowledge for system adjustment, in contrast to state-of-the-art techniques. Experiments show that RusKey exhibits strong performance robustness in diverse workloads, achieving up to 4x better end-to-end performance than the RocksDB system under various settings.
Convex PCA, which was introduced by Bigot et al., is a dimension reduction methodology for data with values in a convex subset of a Hilbert space. This setting arises naturally in many applications, including distributional data in the Wasserstein space of an interval, and ranked compositional data under the Aitchison geometry. Our contribution in this paper is threefold. First, we present several new theoretical results including consistency as well as continuity and differentiability of the objective function in the finite dimensional case. Second, we develop a numerical implementation of finite dimensional convex PCA when the convex set is polyhedral, and show that this provides a natural approximation of Wasserstein geodesic PCA. Third, we illustrate our results with two financial applications, namely distributions of stock returns ranked by size and the capital distribution curve, both of which are of independent interest in stochastic portfolio theory.
We propose a distributed bundle adjustment (DBA) method using the exact Levenberg-Marquardt (LM) algorithm for super large-scale datasets. Most of the existing methods partition the global map to small ones and conduct bundle adjustment in the submaps. In order to fit the parallel framework, they use approximate solutions instead of the LM algorithm. However, those methods often give sub-optimal results. Different from them, we utilize the exact LM algorithm to conduct global bundle adjustment where the formation of the reduced camera system (RCS) is actually parallelized and executed in a distributed way. To store the large RCS, we compress it with a block-based sparse matrix compression format (BSMC), which fully exploits its block feature. The BSMC format also enables the distributed storage and updating of the global RCS. The proposed method is extensively evaluated and compared with the state-of-the-art pipelines using both synthetic and real datasets. Preliminary results demonstrate the efficient memory usage and vast scalability of the proposed method compared with the baselines. For the first time, we conducted parallel bundle adjustment using LM algorithm on a real datasets with 1.18 million images and a synthetic dataset with 10 million images (about 500 times that of the state-of-the-art LM-based BA) on a distributed computing system.
A matrix-free parallel two-level deflation preconditioner for the two-dimensional Helmholtz problems
We propose a matrix-free parallel two-level-deflation preconditioner combined with the Complex Shifted Laplacian preconditioner(CSLP) for the two-dimensional Helmholtz problems. The Helmholtz equation is widely studied in seismic exploration, antennas, and medical imaging. It is one of the hardest problems to solve both in terms of accuracy and convergence, due to scalability issues of the numerical solvers. Motivated by the observation that for large wavenumbers, the eigenvalues of the CSLP-preconditioned system shift towards zero, deflation with multigrid vectors, and further high-order vectors were incorporated to obtain wave-number-independent convergence. For large-scale applications, high-performance parallel scalable methods are also indispensable. In our method, we consider the preconditioned Krylov subspace methods for solving the linear system obtained from finite-difference discretization. The CSLP preconditioner is approximated by one parallel geometric multigrid V-cycle. For the two-level deflation, the matrix-free Galerkin coarsening as well as high-order re-discretization approaches on the coarse grid are studied. The results of matrix-vector multiplications in Krylov subspace methods and the interpolation/restriction operators are implemented based on the finite-difference grids without constructing any coefficient matrix. These adjustments lead to direct improvements in terms of memory consumption. Numerical experiments of model problems show that wavenumber independence has been obtained for medium wavenumbers. The matrix-free parallel framework shows satisfactory weak and strong parallel scalability.
Characterizing shapes of high-dimensional objects via Ricci curvatures plays a critical role in many research areas in mathematics and physics. However, even though several discretizations of Ricci curvatures for discrete combinatorial objects such as networks have been proposed and studied by mathematicians, the computational complexity aspects of these discretizations have escaped the attention of theoretical computer scientists to a large extent. In this paper, we study one such discretization, namely the Ollivier-Ricci curvature, from the perspective of efficient computation by fine-grained reductions and local query-based algorithms. Our main contributions are the following. (a) We relate our curvature computation problem to minimum weight perfect matching problem on complete bipartite graphs via fine-grained reduction. (b) We formalize the computational aspects of the curvature computation problems in suitable frameworks so that they can be studied by researchers in local algorithms. (c) We provide the first known lower and upper bounds on queries for query-based algorithms for the curvature computation problems in our local algorithms framework. En route, we also illustrate a localized version of our fine-grained reduction. We believe that our results bring forth an intriguing set of research questions, motivated both in theory and practice, regarding designing efficient algorithms for curvatures of objects.
We study the problem of reconstructing the Faber--Schauder coefficients of a continuous function $f$ from discrete observations of its antiderivative $F$. Our approach starts with formulating this problem through piecewise quadratic spline interpolation. We then provide a closed-form solution and an in-depth error analysis. These results lead to some surprising observations, which also throw new light on the classical topic of quadratic spline interpolation itself: They show that the well-known instabilities of this method can be located exclusively within the final generation of estimated Faber--Schauder coefficients, which suffer from non-locality and strong dependence on the initial value and the given data. By contrast, all other Faber--Schauder coefficients depend only locally on the data, are independent of the initial value, and admit uniform error bounds. We thus conclude that a robust and well-behaved estimator for our problem can be obtained by simply dropping the final-generation coefficients from the estimated Faber--Schauder coefficients.
Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We show that we can degrade Whisper performance dramatically, or even transcribe a target sentence of our choice, by generating very small input perturbations with Signal Noise Ratio of 35-45dB. We also show that by fooling the Whisper language detector we can very easily degrade the performance of multilingual models. These vulnerabilities of a widely popular open-source model have practical security implications and emphasize the need for adversarially robust ASR.
With a rapidly increasing amount and diversity of remote sensing (RS) data sources, there is a strong need for multi-view learning modeling. This is a complex task when considering the differences in resolution, magnitude, and noise of RS data. The typical approach for merging multiple RS sources has been input-level fusion, but other - more advanced - fusion strategies may outperform this traditional approach. This work assesses different fusion strategies for crop classification in the CropHarvest dataset. The fusion methods proposed in this work outperform models based on individual views and previous fusion methods. We do not find one single fusion method that consistently outperforms all other approaches. Instead, we present a comparison of multi-view fusion methods for three different datasets and show that, depending on the test region, different methods obtain the best performance. Despite this, we suggest a preliminary criterion for the selection of fusion methods.
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