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 69 for “"Nuclear norm"”.
-
System identification via Nuclear norm regularization
… and look at algorithms that rely on nuclear norm regularization for solving this problem. We introduce our own algorithm for solving the problem, based on the alternating direction method of multipliers (ADMM). Our algorithm involves an iterative minimization step, which is solved …
-
Low rank representations of matrices using nuclear norm heuristics
… for approaching the problem. Among them is the nuclear norm heuristic for rank minimization. One aspect of this thesis is the application of the nuclear norm heuristic to the Euclidean distance matrix completion problem. As a special case, the approach is applied to the graph embedding problem. …
-
A Smoothing Newton-BICGStab Method for Least Squares Matrix Nuclear Norm Problems
… method for the least squares nonsymmetric matrix nuclear norm problems. For this type of problems, when linear inequality and second-order cone constraints are present, the dual problem is equivalent to a system of nonsmooth equations. Some smoothing functions are introduced to the nonsmooth …
-
Matrix Completion Models with Fixed Basis Coefficients and Rank Regularized Problems with Hard Constraints
… structure via techniques beyond the widely-used nuclear norm for achieving better performance. In the first part, we propose a rank-corrected procedure for low-rank matrix completion problems with fixed basis coefficients. We establish non-asymptotic recovery error bounds and provide necessary …
-
LOW-RANK MODELS FOR TENSORIAL DATA IN VISUAL ANALYSIS
… of tensor-based linear models use the Tensor Nuclear Norm (TNN) as a convex surrogate of the tensor rank. However, since the tensor nuclear norm is linearly proportional to the sum of singular values, the tensor rank approximation using the tensor nuclear norm may become problematic if the …
-
LOW RANK AND SPARSE MODELING FOR DATA ANALYSIS
… One popular heuristic method is to use the nuclear norm to approximate the rank of a matrix. Despite the success of nuclear norm minimization in capturing the low intrinsic-dimensionality of data, the nuclear norm minimizes not only the rank, but also the variance of matrix and may not be a …
-
Channel Estimation in Massive Multi-User MIMO Systems Based on Low-Rank Matrix Approximation
… is studied. Thus, two-channel estimation namely “nuclear norm (NN)” and “iterative weighted nuclear norm (IWNN)” approximation techniques are proposed to solve the channel estimation problem in both systems. First, channel estimation in a single-cell TDD massive MU-MIMO system is formulated as a …
-
Constrained relative entropy minimization with applications to multitask learning
… Gaussian process prior with inference subject to nuclear norm expectation constraints. In addition, a novel nonparametric model is proposed for multitask bipartite ranking. The proposed model combines a hierarchical matrix-variate Gaussian process prior with inference subject to ordering …
-
Leveraging Sparsity and Low Rank for Large-Scale Networks and Data Science
… on every bit of our lives, churning out enormous streams of raw data in a wide variety of formats. While big data may bring ``big blessings," there are formidable challenges in dealing with large-scale datasets. The sheer volume of data makes it often impossible to run analytics using …
-
Fixed Point Iteration Algorithms for Low-rank Matrix Completion
… the recovery of low-rank matrix can be done via nuclear norm minimization, a convex program. Scalable and fast algorithms are essential as the practical matrix completion tasks always occur on a large scale. Here we study two algorithms and generalize the uni ed framework of xed point iteration …
-
Nonconvex Optimization and Model Representation with Applications in Control Theory and Machine Learning
… complexity. We present two results, the Hankel nuclear norm regularization method for learning a low order system, and the overparameterized representation for linear meta-learning. We study dynamical system identification in the first result. We assume the true system order is low. A low system …
-
Reconstructing the connectome from an ensemble of measurements
… can be formulated naturally in terms of nuclear norm minimization techniques. It is our belief that the presented methods will allow the acquisition of future connectomes with an order of magnitude reduction in experimental effort, as well as significantly outperform the simpler inference …
-
Rank Reduction with Convex Constraints
… of rank-constrained unitarily invariant norms. These minorizers can be used to construct optimal convex relaxations for the original non-convex problem. Unlike other methods such as nuclear norm regularization, this approach benefits from having verifiable a posterior conditions for which …
-
Mirror descent for high-dimensional statistical models
… descent via a quantity explicitly related to the nuclear norm, Frobenius norm, and the von Neumann entropy. Assuming either a restricted isometry property or the setting of matrix completion, we obtain recovery guarantees for mirror descent that improve upon existing theoretical results for …
-
Essays in Problems in Sequential Decisions and Large-Scale Randomized Algorithms
… a central limit theorem (CLT) with a different normalization than Renyi's classical CLT, and in the constricted case we find convergence in distribution to an unbounded random variable. In the second part of this dissertation, we put forward two large-scale randomized algorithms. We propose a …
-
Optimization Methods for 3D Reconstruction : Depth Sensors, Distance Functions and Low-Rank Models
… of replacing the rank function with the nuclear norm.
-
Methods and Theory for Nonparametric Inference In High-dimensional Settings
… In the final project, we theoretically show that nuclear-norm penalization used for recovering low-rank matrices, remains effective even when the underlying matrices are generated by a low-dimensional non-linear manifold. The convergence rate can be expressed as a function of the size of the …
-
Low-rank matrix recovery: blind deconvolution and efficient sampling of correlated signals
… signals can be reconstructed using the familiar nuclear-norm minimization. The sampling theorems derived for each of the sampling architecture show that the LRMR framework produces the Shannon-Nyquist performance for the sub-Nyquist acquisition of correlated signals. In the final part, we study …
-
Graph Trace Regression Estimation
… in the trace regression model with minimum nuclear norm among all candidates matrices satisfying the designated convex constraints. The algorithm iteratively produces a sequence of matrices $\{\mathbf{X}^k,\tilde{\Theta}^k\}$ where soft-thresholding is operated on the singular values of the …
-
Computational Methods for Computer Vision : Minimal Solvers and Convex Relaxations
… Recently convex relaxations, such as the nuclear norm, have been used to make these problems tractable. In this thesis we present new convex relaxations for rank-based optimization which avoid drawbacks of previous approaches and provide tighter relaxations. We evaluate our methods on a …
Page 1 of 4