Alert button
Picture for Phil Romero

Phil Romero

Alert button

Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution

Jun 21, 2023
Phil Romero, Manish Bhattarai, Christian F. A. Negre, Anders M. N. Niklasson, Adetokunbo Adedoyin

Figure 1 for Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution
Figure 2 for Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution
Figure 3 for Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution
Figure 4 for Matrix Diagonalization as a Board Game: Teaching an Eigensolver the Fastest Path to Solution

Matrix diagonalization is at the cornerstone of numerous fields of scientific computing. Diagonalizing a matrix to solve an eigenvalue problem requires a sequential path of iterations that eventually reaches a sufficiently converged and accurate solution for all the eigenvalues and eigenvectors. This typically translates into a high computational cost. Here we demonstrate how reinforcement learning, using the AlphaZero framework, can accelerate Jacobi matrix diagonalizations by viewing the selection of the fastest path to solution as a board game. To demonstrate the viability of our approach we apply the Jacobi diagonalization algorithm to symmetric Hamiltonian matrices that appear in quantum chemistry calculations. We find that a significant acceleration can often be achieved. Our findings highlight the opportunity to use machine learning as a promising tool to improve the performance of numerical linear algebra.

* 14 pages 
Viaarxiv icon

The ISTI Rapid Response on Exploring Cloud Computing 2018

Jan 04, 2019
Carleton Coffrin, James Arnold, Stephan Eidenbenz, Derek Aberle, John Ambrosiano, Zachary Baker, Sara Brambilla, Michael Brown, K. Nolan Carter, Pinghan Chu, Patrick Conry, Keeley Costigan, Ariane Eberhardt, David M. Fobes, Adam Gausmann, Sean Harris, Donovan Heimer, Marlin Holmes, Bill Junor, Csaba Kiss, Steve Linger, Rodman Linn, Li-Ta Lo, Jonathan MacCarthy, Omar Marcillo, Clay McGinnis, Alexander McQuarters, Eric Michalak, Arvind Mohan, Matt Nelson, Diane Oyen, Nidhi Parikh, Donatella Pasqualini, Aaron s. Pope, Reid Porter, Chris Rawlings, Hannah Reinbolt, Reid Rivenburgh, Phil Romero, Kevin Schoonover, Alexei Skurikhin, Daniel Tauritz, Dima Tretiak, Zhehui Wang, James Wernicke, Brad Wolfe, Phillip Wolfram, Jonathan Woodring

Figure 1 for The ISTI Rapid Response on Exploring Cloud Computing 2018
Figure 2 for The ISTI Rapid Response on Exploring Cloud Computing 2018
Figure 3 for The ISTI Rapid Response on Exploring Cloud Computing 2018
Figure 4 for The ISTI Rapid Response on Exploring Cloud Computing 2018

This report describes eighteen projects that explored how commercial cloud computing services can be utilized for scientific computation at national laboratories. These demonstrations ranged from deploying proprietary software in a cloud environment to leveraging established cloud-based analytics workflows for processing scientific datasets. By and large, the projects were successful and collectively they suggest that cloud computing can be a valuable computational resource for scientific computation at national laboratories.

Viaarxiv icon