n2p2

n2p2 is used for neural network training. n2p2 2.3.0 is the latest release, tag e51667abf784bb9a6fd659857b6a9a878fdc6a90 (2024-11-23).

Versions

Registry pins for this code.

Role	Ref	Commit	Source
neural network training	master	29b9c9f10b1a	https://github.com/CompPhysVienna/n2p2

Best cost

A shorter bar is a lower cost on a log scale shared by the codes of this problem.

A shorter bar is a lower cost on a log scale shared by the codes of this problem.

Results

Ranked rows for this code, one version and one method on each row. PAR-2 counts a finished run as the calls it used and a failed run as twice the cap. An archived row shows the average it published, and its PAR-2 applies that rule to the failures the entry records. Scoring rules.

Every ranked row for this code. Select a column heading to sort.

Suite	Problem	Row	Family	Family rank	Unit	PAR-2	Published	Median calls	Mean calls	Hessians	FD calls	Failures	Runs
Machine learning optimization	Ethene	n2p2 (2.3.0) · Kalman energy	Minimizers	1	loss-gradient evaluations	17397.1		10000	9397.12	0	0	crash 0, divergence 0, cap 40, wrong_stationary 0	50
Machine learning optimization	Ethene	n2p2 (2.3.0) · Kalman force	Minimizers	2	loss-gradient evaluations	60000		30000	30000	0	0	crash 0, divergence 0, cap 50, wrong_stationary 0	50
Machine learning optimization	EMT Pt 38 nanoparticle	n2p2 (2.3.0) · Kalman energy	Minimizers	1	loss-gradient evaluations	25.02		14	25.02	0	0	crash 0, divergence 0, cap 0, wrong_stationary 0	50
Machine learning optimization	EMT Pt 38 nanoparticle	n2p2 (2.3.0) · Kalman force	Minimizers	2	loss-gradient evaluations	60000		30000	30000	0	0	crash 0, divergence 0, cap 50, wrong_stationary 0	50