Browsing Combinatorics and Optimization by Supervisor "Vavasis, Stephen"
Now showing items 1-6 of 6
-
Applications of Stochastic Gradient Descent to Nonnegative Matrix Factorization
(University of Waterloo, 2019-07-15)We consider the application of stochastic gradient descent (SGD) to the nonnegative matrix factorization (NMF) problem and the unconstrained low-rank matrix factorization problem. While the literature on the SGD algorithm ... -
A quadratic programming approach to find faces in robust nonnegative matrix factorization
(University of Waterloo, 2017-08-29)Nonnegative matrix factorization (NMF) is a popular dimensionality reduction technique because it is easily interpretable and can discern useful features. For a given matrix M (dimension n x m) whose entries are nonnegative ... -
Recovery Guarantees for Graph Clustering Problems
(University of Waterloo, 2021-12-06)Graph clustering is widely-studied unsupervised learning problem in which the task is to group similar entities together based on observed pairwise entity interactions. This problem has applications in diverse domains such ... -
Simple Termination Criteria for Stochastic Gradient Descent Algorithm
(University of Waterloo, 2021-04-09)Stochastic gradient descent (SGD) algorithm is widely used in modern mathematical optimization. Because of its scalability and ease of implementation, SGD is usually preferred to other methods including the gradient descent ... -
Solving Saddle Point Formulations of Linear Programs with Frank-Wolfe
(University of Waterloo, 2023-08-24)The problem of solving a linear program (LP) is ubiquitous in industry, yet in recent years the size of linear programming problems has grown and continues to do so. State-of-the-art LP solvers make use of the Simplex ... -
Sum-of-norms clustering: theoretical guarantee and post-processing
(University of Waterloo, 2020-09-11)Sum-of-norms clustering is a method for assigning n points in d-dimensional real space to K clusters, using convex optimization. Recently, Panahi et al. proved that sum-of-norms clustering is guaranteed to recover a mixture ...