11 citations · 22 across the 7 of their papers we have counts for
7 papers
General Constrained Matrix Optimization
Casey Garner, Gilad Lerman, Shuzhong Zhang
This paper presents and analyzes the first matrix optimization model which allows general coordinate and spectral constraints. The breadth of problems our model covers is exemplifi…
Novel Optimization Techniques for Parameter Estimation
Chenyu Wu, Nuozhou Wang, Casey Garner +2
In this paper, we introduce a new optimization algorithm that is well suited for solving parameter estimation problems. We call our new method cubic regularized Newton with affine…
Improved Convergence Factor of Windowed Anderson Acceleration for Symmetric Fixed-Point Iterations
Casey Garner, Gilad Lerman, Teng Zhang
This paper studies the commonly utilized windowed Anderson acceleration (AA) algorithm for fixed-point methods, . It provides the first proof that when the op…
Spectrally Constrained Optimization
Casey Garner, Gilad Lerman, Shuzhong Zhang
We investigate how to solve smooth matrix optimization problems with general linear inequality constraints on the eigenvalues of a symmetric matrix. We present solution methods to…
Cubic-Regularized Newton for Spectral Constrained Matrix Optimization and its Application to Fairness
Casey Garner, Gilad Lerman, Shuzhong Zhang
Matrix functions are utilized to rewrite smooth spectral constrained matrix optimization problems as smooth unconstrained problems over the set of symmetric matrices which are then…
HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
Vincent Dumont, Casey Garner, Anuradha Trivedi +6
We present a new software, HYPPO, that enables the automatic tuning of hyperparameters of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) methods,…
Linearly-Convergent FISTA Variant for Composite Optimization with Duality
Casey Garner, Shuzhong Zhang
Many large-scale optimization problems can be expressed as composite optimization models. Accelerated first-order methods such as the fast iterative shrinkage-thresholding algorith…