Skip to main content
Cyber Security and Resilience Community
Cyber Security and Resilience Community
People
Faculty
Research Scientists
Postdoctoral Fellows
All People
Research Groups
Cyber Security and Resilience Technology (CyberSaR)
Roberto Di Pietro Research Group (R-Pietro)
Security Research Bearing Experimental Results (SeRBER)
Research Strategy
PETScML
On the Use of "Conventional" Unconstrained Minimization Solvers for Training Regression Problems in Scientific Machine Learning
Stefano Zampini, Senior Research Scientist, Hierarchical Computations on Manycore Architectures
Mar 13, 12:00
-
13:00
B9 L2 R2325
petsc
PETScML
machine learning
This talk introduces PETScML, a framework leveraging traditional second-order optimization solvers for use within scientific machine learning, demonstrating improved generalization capabilities over gradient-based methods routinely adopted in deep learning.
