Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 29 for “"Kernel matrices"”.
-
Clustering using similarity and kernel matrices
… sources and/or feature spaces and iii) multiple kernel learning, where a kernel that suits the data is learned together with the cluster assignments. Usually, the kernel is parametrized as a combination of some predefined kernels, called basis kernels, and we wish to infer appropriate values for …
-
Convergence Rates of Spectral Distribution of Random Inner Product Kernel Matrices
… the first part, we focus on random inner product kernel matrices. Under various assumptions, many authors have proved that the limiting empirical spectral distribution (ESD) of such matrices A converges to the Marchenko- Pastur distribution. Here, we establish the corresponding rate of …
-
A Bayesian Variable Selection Model for Semi-Continuous Response Using Gaussian Process
… of the model through the construction of the kernel matrices. I have employed the Nystr\"{o}m approximation for kernel matrices to reduce the computational complexity that occurs when working with kernel matrices and large sample sizes. I perform simulation studies and determine my method is …
-
Fast Kernel Matrix Approximations By Series Expansions
Kernel functions are used in a variety of scientific settings to measure relationships or interactions between elements of a vector space. For example, in machine learning, kernel functions are often used to describe similarity or covariance between data points in a feature space. In physics, one …
-
New Parallel Algorithms for Large-Scale Matrix Computations
… for better performance. For large sparse matrices, we propose the communication-reduced parallel sparse-dense matrix multiplication (CRP-SpMM) algorithm. This algorithm can benefit from existing sparse matrix partitioning methods for sparse matrix-dense vector multiplication (SpMV), and …
-
Additive Kernel Methods with Fourier Acceleration
Kernel matrices are crucial in many learning tasks, such as kernel ridge regression, support vector machines, or Gaussian process regression. One of the main computational bottlenecks when working with large-scale kernel-based learning is dealing with the large and typically dense kernel matrix. …
-
Statistical analysis for network-based models with applications to genetic association and prediction
… genetic random field (GGRF) and the sequence kernel association test (SKAT) methods under different disease scenarios. We find that our method outperforms the other two methods when (i) the rare variants have the major contribution to the disease, or (ii) the genetic effects vary in different …
-
Identification of parametric finite-element models using experimental modal data
… a set of scalar parameters multiplying element kernel matrices. The parameters of the finite-element model can represent stiffness and inertia properties, as well as axial forces if linearized buckling is assumed. Optimization of an orthogonality-based objective functional is employed to …
-
oASIS: Adaptive Column Sampling for Kernel Matrix Approximation
Kernel or similarity matrices are essential for many state-of-the-art approaches to classification, clustering, and dimensionality reduction. For large datasets, the cost of forming and factoring such kernel matrices becomes intractable. To address this challenge, we introduce a new adaptive …
-
Kernel Methods for Regression and Classification: Classical and Neural-Inspired Approaches
… non-parametric regression model involves the kernel methods. We will define the kernel function, build several canonical kernel functions, present reproducing kernel Hilbert space theory, and provide a proof of the Representer Theorem, which will allow us to introduce kernels into a regression …
-
The science of high performance algorithms for hierarchical matrices
Many matrices in scientific computing, statistical inference, and machine learning exhibit sparse and low-rank structure. Typically, such structure is exposed by appropriate matrix permutation of rows and columns, and exploited by constructing an hierarchical approximation. That is, the matrix can …
-
Spectral machine learning
… thesis we develop a spectral approach to large kernel matrices, graphs and the Hessians of neural networks. This approach paves the way for efficient and improved inference schemes, novel algorithms and theoretical results. The first contribution of the thesis is the development of a novel …
-
Learning and Optimisation of Representations in Deep Learning
… on the learned function, rather than the weight matrices. Recent work (Deep Kernel Machines) studies representation learning by modifying the infinite-width limit in Neural Network Gaussian Process models, which don’t perform representation learning, so that their intermediate kernel matrices …
-
Robust optimization for plastic closed-loop supply chains: advancing data-driven models with kernel weight adjustment and fairness metrics
… across varying conservatism levels, a single-Kernel learning-based approach is developed, wherein the weights of the basis kernel matrices are adjusted based on the data’ dispersion in each direction. Additionally, this thesis introduces a Robust Fairness (RF) index to evaluate and compare the …
-
Kernel dimension reduction approaches for multivariate process control
… control charts based on the eigen-analysis of kernel matrices. The core idea behind our proposed techniques is to develop a theoretically rigorous methodology for multivariate statistical process control. We use scalp-recorded electroencephalograms (EEGs) as our real-world multivariate data …
-
Rank-1 lattice rules for uncertainty quantification of partial differential equations with random input
… a multilevel extension to a lattice-based kernel approximation method for approximating solutions to PDEs with periodic random coefficients over the parametric domain. Full cost and error analysis (including regularity theory) is presented showing that the multilevel algorithm can achieve …
-
Large-scale non-linear prediction with applications
… standard non-linear algorithms based on either kernels (e.g., kernel support vector machines and kernel ridge regression) or decision trees (e.g., gradient boosted decision trees) often yield superior predictive performance on various machine learning tasks compared to linear methods; however, …
-
Novel Methods for Approximate Bayesian Inference of Independent and Evolutionarily Dependent Data
… The gamma-EP algorithm is extended to use kernel matrices and applied to oncogenic single nucleotide variant (SNV) classification.<br/><br/>The second method is a new phylogenetic regression model called Phylogenetic Relevance Vector Machine (PhyRVM). We present the first analytical …
-
Studies on Kernel Learning and Independent Component Analysis
A crucial step in kernel-based learning is the selection of a proper kernel function or kernel matrix. Multiple kernel learning (MKL), in which a set of kernels are assessed during the learning time, was recently proposed to solve the kernel selection problem. The goal is to estimate a suitable …
-
Algebraic and Geometric Structures in Machine Learning
… the problem of learning under symmetry with kernel methods. In particular, we demonstrate that invariances have a pronounced effect on the rank of kernel matrices, with this rank becoming independent of the data's dimension in key examples. Relating this to the phenomenon of representation …
Page 1 of 2