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 11 of 11 for “"Sparse tensors"”.
-
Incidence networks for Geometric Deep Learning
Sparse incidence tensors can represent a variety of structured data. For example, we may represent attributed graphs using their node-node, node-edge, or edge-edge incidence matrices. In higher dimensions, incidence tensors can represent simplicial complexes and polytopes. In this work, we …
-
Scalable Algorithms for Hypergraph Analytics using Symmetric Tensor Decompositions
Tensors are higher-dimension generalizations of matrices and are used to represent multi-dimensional data. Tensor-based methods are receiving renewed attention in recent years due to their prevalence in diverse real-world applications. Symmetric tensors are an important class of tensors, arising in …
-
High-Performance Sparse Tensor Factorization: Algorithms for Hyper-Sparse Streaming Data and Scalable Non-Negative Least Squares Solvers
… that arise when factorizing real-world sparse tensors, which are characterized by irregular memory access and significant memory overhead. To overcome these issues, we present novel optimizations that include reformulating core computations and developing dynamic data encoding …
-
Algorithms for Large-Scale Sparse Tensor Factorization
… useful insights and make better decisions. The tensors that arise in these domains are increasingly large, sparse, and high dimensional. Factoring these tensors is computationally expensive, if not infeasible. The ubiquity of multi-core processors and large-scale clusters motivates the …
-
High-Dimensional Generative Models for 3D Perception
… for data learning. Here, we design several sparse learning-based approaches for high-dimensional data that effectively tackle multiple perception problems, including data filtering, data recovery, and data retrieval. The frameworks offer generative solutions for analyzing complex and …
-
Hashed Coordinate Sparse Tensor Storage with MATLAB
<p>Tensors, or <em>n</em>-way arrays, are incredibly useful for storing indexable data in an arbitrary number of dimensions. Interest in tensor analysis using tensor decomposition has expanded to a variety of fields, including data mining, signal processing, computer vision, and machine learning. …
-
Structured Sparsity-Aware Hardware-Software Co-Design for Deep Neural Network Acceleration
… Next, we present VEGETA, a flexible structured sparse matrix engine extending a dense matrix engine with flexible structured sparsity support. In addition, we show how VEGETA engines can be used for different sparsity granularities, such as network-wise, layer-wise, tile-wise, and row-wise. …
-
SFGNets: Machine Learning Tools for SuperFGD Neutrino Detector: Master Thesis on the Development of Neural Networks for the Data Analysis of the Super Fine Grained Detector of the Near Detector 280 Meters of the Tokai to Kamiokande Experiment
… with a Convolutional Neural Network (CNN) on sparse tensors (we obtained 83\% score compared to 75\% with a decision tree); second fit the trajectory points of escaping particles with a transformer encoder (1.21 mm average distance to the truth compared to 3.06 mm with a Bayesian filter); …
-
Computational developments for ab initio many-body theory
… coupled cluster program which implements a sparse tensor storage scheme and efficient tensor contraction algorithms. A distributed memory data structure for these large, sparse tensors is used so that the code can run in a high-performance computing setting, and can thus handle the …
-
Efficient Neural Network Inference on Resource-Constrained Devices
… be replaced with zeroes, leaving a network with sparse tensors. Most research focuses on using this sparsity to accelerate computations, while its use for compression is rarely discussed. This is addressed by developing two encoding schemes for sparse neural network tensors, which achieve both …
-
Scalable tensor decompositions in high performance computing environments
… operations in cases when the tensor is dense or sparse. Our contributions include: 1) applying memoization to overcome the curse of dimensionality challenge that exists in a sequence of tensor operations; 2) addressing the challenge of mode orientation through a novel tensor format HICOO and …