Zobrazeno 1 - 10
of 140
pro vyhledávání: '"Marcia, Roummel F."'
Autor:
Lu, Yu, Marcia, Roummel F.
The negative binomial model, which generalizes the Poisson distribution model, can be found in applications involving low-photon signal recovery, including medical imaging. Recent studies have explored several regularization terms for the negative bi
Externí odkaz:
http://arxiv.org/abs/2408.16622
In many applications such as medical imaging, the measurement data represent counts of photons hitting a detector. Such counts in low-photon settings are often modeled using a Poisson distribution. However, this model assumes that the mean and varian
Externí odkaz:
http://arxiv.org/abs/2408.16117
Matrix completion focuses on recovering missing or incomplete information in matrices. This problem arises in various applications, including image processing and network analysis. Previous research proposed Poisson matrix completion for count data w
Externí odkaz:
http://arxiv.org/abs/2408.16113
In this work, we consider methods for large-scale and nonconvex unconstrained optimization. We propose a new trust-region method whose subproblem is defined using a so-called "shape-changing" norm together with densely-initialized multipoint symmetri
Externí odkaz:
http://arxiv.org/abs/2209.12057
Autor:
Marcia, Roummel F.
Publikováno v:
Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses
Thesis (Ph. D.)--University of California, San Diego, 2002.
Vita. Includes bibliographical references (leaves 191-198).
Vita. Includes bibliographical references (leaves 191-198).
Externí odkaz:
http://wwwlib.umi.com/cr/ucsd/fullcit?p3044769
Publikováno v:
SIAM Journl. Sci. Comput. 44(1), 2022
For optimization problems with linear equality constraints, we prove that the (1,1) block of the inverse KKT matrix remains unchanged when projected onto the nullspace of the constraint matrix. We develop reduced compact representations of the limite
Externí odkaz:
http://arxiv.org/abs/2101.11048
Autor:
Rafati, Jacob, Marcia, Roummel F.
Deep learning algorithms often require solving a highly non-linear and nonconvex unconstrained optimization problem. Methods for solving optimization problems in large-scale machine learning, such as deep learning and deep reinforcement learning (RL)
Externí odkaz:
http://arxiv.org/abs/1909.01994
Autor:
Rafati, Jacob, Marcia, Roummel F.
Reinforcement Learning (RL) algorithms allow artificial agents to improve their action selections so as to increase rewarding experiences in their environments. Deep Reinforcement Learning algorithms require solving a nonconvex and nonlinear unconstr
Externí odkaz:
http://arxiv.org/abs/1811.02693
Machine learning (ML) problems are often posed as highly nonlinear and nonconvex unconstrained optimization problems. Methods for solving ML problems based on stochastic gradient descent are easily scaled for very large problems but may involve fine-
Externí odkaz:
http://arxiv.org/abs/1807.00251
We consider a family of dense initializations for limited-memory quasi-Newton methods. The proposed initialization exploits an eigendecomposition-based separation of the full space into two complementary subspaces, assigning a different initializatio
Externí odkaz:
http://arxiv.org/abs/1710.02396